Upload folder using huggingface_hub

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/config.json

@@ -0,0 +1,26 @@
+{
+ "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 16384,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 1000000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.33.1",
+ "use_cache": true,
+ "vocab_size": 32016
+}

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "transformers_version": "4.33.1"
+}

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/info.txt

@@ -0,0 +1,2 @@
+peft model path: /home/lune/nas2/Projects/code_editing/checkpoints/CodeLlama-7b-Instruct-hf/code-50k-fixed-half-feedback-codegen-only/checkpoint-2300
+Model saved to codellama/CodeLlama-7b-Instruct-hf

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b06946bc12d76f5d805de00447ccaa97df38ca0cab33f1d8b98c9e7ba2f44cc
+size 9976751194

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fec1941a4cb7f02c584bc45c0e21b083fd66bf3b877fff996a736bb2132aa4d
+size 3500441859

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 13477093376
+ },
+ "weight_map": {
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+ }
+}

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

editor/code-50k-fixed-half-feedback-codegen-only-checkpoint-2300-merged/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eot_token": "▁<EOT>",
+ "fill_token": "<FILL_ME>",
+ "legacy": null,
+ "middle_token": "▁<MID>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "prefix_token": "▁<PRE>",
+ "sp_model_kwargs": {},
+ "suffix_token": "▁<SUF>",
+ "tokenizer_class": "CodeLlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "use_default_system_prompt": false
+}

editor/critic/config.json

@@ -0,0 +1,26 @@
+{
+ "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 16384,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 1000000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.33.1",
+ "use_cache": true,
+ "vocab_size": 32016
+}

editor/critic/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "transformers_version": "4.33.1"
+}

editor/critic/info.txt

@@ -0,0 +1,2 @@
+peft model path: /convei_nas2/hjchae/code-editing/checkpoints/CodeLlama-7b-Instruct-hf/code-50k-feedback-strict-filtered-feedback-only/checkpoint-5000
+Model saved to codellama/CodeLlama-7b-Instruct-hf

editor/critic/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7644da6d1149647d20c1c10e9d711273ae6db1bc8c216ec02566c14a212094b
+size 9976751194

editor/critic/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6e0aa3af351a5a45d1abede990a05ab33e69b80e8f762fdd9750afa8dbc8f2
+size 3500441859

editor/critic/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 13477093376
+ },
+ "weight_map": {
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+ }
+}

editor/critic/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

editor/critic/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

editor/critic/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eot_token": "▁<EOT>",
+ "fill_token": "<FILL_ME>",
+ "legacy": null,
+ "middle_token": "▁<MID>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "prefix_token": "▁<PRE>",
+ "sp_model_kwargs": {},
+ "suffix_token": "▁<SUF>",
+ "tokenizer_class": "CodeLlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "use_default_system_prompt": false
+}

editor/dpo/added_tokens.json

@@ -0,0 +1,9 @@
+{
+ "</s>": 2,
+ "<s>": 1,
+ "<unk>": 0,
+ "▁<EOT>": 32010,
+ "▁<MID>": 32009,
+ "▁<PRE>": 32007,
+ "▁<SUF>": 32008
+}

editor/dpo/config.json

@@ -0,0 +1,27 @@
+{
+ "_name_or_path": "/convei_nas2/hjchae/code-editing/checkpoints/CodeLlama-7b-Instruct-hf/code-50k-feedback-strict-filtered-feedback-only-checkpoint-5000-merged",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 16384,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 1000000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.34.0",
+ "use_cache": true,
+ "vocab_size": 32016
+}

editor/dpo/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "transformers_version": "4.34.0"
+}

editor/dpo/info.txt

@@ -0,0 +1,2 @@
+peft model path: /home/taeyoon/nas2/code-editing/dpo/checkpoints/dpo-codellama2-only-feedback-new_short/checkpoint-750
+Model saved to /convei_nas2/hjchae/code-editing/checkpoints/CodeLlama-7b-Instruct-hf/code-50k-feedback-strict-filtered-feedback-only-checkpoint-5000-merged

editor/dpo/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b99abb171cb6b77c2969e05862fff1a123f330f52f62687aacbdb34b478f71
+size 9976751194

editor/dpo/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ccd973de1cc29ee43e84e4a800118a01bbc618a03123af8b3ebeabe537de2c
+size 3500441859

editor/dpo/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 13477093376
+ },
+ "weight_map": {
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+ }
+}

editor/dpo/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>",
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": "<s>",
+ "eos_token": "</s>",
+ "unk_token": "<unk>"
+}

editor/dpo/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

editor/dpo/tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32007": {
+ "content": "▁<PRE>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32008": {
+ "content": "▁<SUF>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32009": {
+ "content": "▁<MID>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32010": {
+ "content": "▁<EOT>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>",
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "eot_token": "▁<EOT>",
+ "fill_token": "<FILL_ME>",
+ "legacy": null,
+ "middle_token": "▁<MID>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "prefix_token": "▁<PRE>",
+ "sp_model_kwargs": {},
+ "suffix_token": "▁<SUF>",
+ "tokenizer_class": "CodeLlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": false
+}

editor/editor/config.json

@@ -0,0 +1,26 @@
+{
+ "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 16384,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 1000000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.33.1",
+ "use_cache": true,
+ "vocab_size": 32016
+}

editor/editor/generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "transformers_version": "4.33.1"
+}

editor/editor/info.txt

@@ -0,0 +1,2 @@
+peft model path: /home/lune/nas2/Projects/code_editing/checkpoints/CodeLlama-7b-Instruct-hf/code-50k-fixed-half-feedback-codegen-only/checkpoint-2300
+Model saved to codellama/CodeLlama-7b-Instruct-hf

editor/editor/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b06946bc12d76f5d805de00447ccaa97df38ca0cab33f1d8b98c9e7ba2f44cc
+size 9976751194

editor/editor/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fec1941a4cb7f02c584bc45c0e21b083fd66bf3b877fff996a736bb2132aa4d
+size 3500441859

editor/editor/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 13477093376
+ },
+ "weight_map": {
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+ }
+}

editor/editor/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

editor/editor/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

editor/editor/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eot_token": "▁<EOT>",
+ "fill_token": "<FILL_ME>",
+ "legacy": null,
+ "middle_token": "▁<MID>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "prefix_token": "▁<PRE>",
+ "sp_model_kwargs": {},
+ "suffix_token": "▁<SUF>",
+ "tokenizer_class": "CodeLlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "use_default_system_prompt": false
+}

editor/selector/config.json

@@ -0,0 +1,32 @@
+{
+ "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+ "architectures": [
+ "LlamaForSequenceClassification"
+ ],
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "id2label": {
+ "0": "LABEL_0"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "label2id": {
+ "LABEL_0": 0
+ },
+ "max_position_embeddings": 16384,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 1000000,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.33.1",
+ "use_cache": true,
+ "vocab_size": 32016
+}

editor/selector/info.txt

@@ -0,0 +1,2 @@
+peft model path: /home/lune/nas2/Projects/code_editing/checkpoints/CodeLlama-7b-Instruct-hf/DLI-Lab/code-dpo-classification-trainset--dpo-classification/checkpoint-2600
+Model saved to codellama/CodeLlama-7b-Instruct-hf

editor/selector/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a2b1d11b2f11a57e4080f374ca183c1a573d1edd27f2026b997748f8c7527e
+size 9976751194

editor/selector/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ca303b087c251558d9a05c07f9fb402e96c01219f7d7fc16abb26632a04d64
+size 3238174915

editor/selector/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 13214826496
+ },
+ "weight_map": {
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin",
+ "score.weight": "pytorch_model-00002-of-00002.bin"
+ }
+}

editor/selector/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

editor/selector/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

editor/selector/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+ "additional_special_tokens": [
+ "▁<PRE>",
+ "▁<MID>",
+ "▁<SUF>",
+ "▁<EOT>"
+ ],
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eot_token": "▁<EOT>",
+ "fill_token": "<FILL_ME>",
+ "legacy": null,
+ "middle_token": "▁<MID>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "prefix_token": "▁<PRE>",
+ "sp_model_kwargs": {},
+ "suffix_token": "▁<SUF>",
+ "tokenizer_class": "CodeLlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "use_default_system_prompt": false
+}