Training in progress, step 1000

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "[PAD]": 256000
+}

config.json

@@ -0,0 +1,30 @@
+{
+ "_name_or_path": "crodri/Fundacional_100percent",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 11008,
+ "max_position_embeddings": 8192,
+ "mlp_bias": false,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 8,
+ "pad_token_id": 2,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000.0,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.44.2",
+ "use_cache": false,
+ "vocab_size": 256001
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964fc9b9cd0a1011b588416f40ec478c23c07142178c25225e6286e998be8f37
+size 4987078016

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7981e610175f5fbd630adc519d500f5bf80c2dd47965e79a3dbc9c976bf80905
+size 4978875576

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f26eabb869c669641443b6a472c591f50bee1e850febdc641f4488c03130ba0
+size 4962098288

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad172feacf9d5dae6e86068f874b44b6d3ac729c9fed1e053fafc937056cc1b8
+size 4962098312

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37151dfd1206070708458560b80c676f5ba7a1c9d87a2822496d0da09f1a2341
+size 4962098312

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd077d1f098abf2b8f88ea3d526015f968c90054e73980889a3f124ddb71115c
+size 2025966392

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e3d15b945bd05a3c80c83273eb1fad02a1c7f7a5b9267cd0955d7c04ada5e0
+size 4194320512

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 31072501760
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00007-of-00007.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+ "model.norm.weight": "model-00006-of-00007.safetensors"
+ }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b45e152a4ca7855716e31502bae3894545dd86adeab34b72d8540398a303e98
+size 19092730

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa490e57cebce5cb1a0a5b1a5d3fa4de05aee53dc3a44791f1c3401db44d802d
+size 4813274

tokenizer_config.json

@@ -0,0 +1,1107 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": "<|reserved_token_1|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": "<|reserved_token_2|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": "<|reserved_token_3|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "9": {
+ "content": "<|reserved_token_4|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "10": {
+ "content": "<|reserved_token_5|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "11": {
+ "content": "<|reserved_token_6|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "12": {
+ "content": "<|reserved_token_7|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "13": {
+ "content": "<|reserved_token_8|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "14": {
+ "content": "<|reserved_token_9|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "15": {
+ "content": "<|reserved_token_10|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "16": {
+ "content": "<|reserved_token_11|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "17": {
+ "content": "<|reserved_token_12|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "18": {
+ "content": "<|reserved_token_13|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "19": {
+ "content": "<|reserved_token_14|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "20": {
+ "content": "<|reserved_token_15|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "21": {
+ "content": "<|reserved_token_16|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "22": {
+ "content": "<|reserved_token_17|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "23": {
+ "content": "<|reserved_token_18|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "24": {
+ "content": "<|reserved_token_19|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "25": {
+ "content": "<|reserved_token_20|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "26": {
+ "content": "<|reserved_token_21|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "27": {
+ "content": "<|reserved_token_22|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "28": {
+ "content": "<|reserved_token_23|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "29": {
+ "content": "<|reserved_token_24|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "<|reserved_token_25|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "31": {
+ "content": "<|reserved_token_26|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32": {
+ "content": "<|reserved_token_27|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "33": {
+ "content": "<|reserved_token_28|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "34": {
+ "content": "<|reserved_token_29|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "35": {
+ "content": "<|reserved_token_30|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "36": {
+ "content": "<|reserved_token_31|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "37": {
+ "content": "<|reserved_token_32|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "38": {
+ "content": "<|reserved_token_33|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "39": {
+ "content": "<|reserved_token_34|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "40": {
+ "content": "<|reserved_token_35|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "41": {
+ "content": "<|reserved_token_36|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "42": {
+ "content": "<|reserved_token_37|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "43": {
+ "content": "<|reserved_token_38|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "44": {
+ "content": "<|reserved_token_39|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "45": {
+ "content": "<|reserved_token_40|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "46": {
+ "content": "<|reserved_token_41|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "47": {
+ "content": "<|reserved_token_42|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "48": {
+ "content": "<|reserved_token_43|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "49": {
+ "content": "<|reserved_token_44|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "50": {
+ "content": "<|reserved_token_45|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "51": {
+ "content": "<|reserved_token_46|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "52": {
+ "content": "<|reserved_token_47|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "53": {
+ "content": "<|reserved_token_48|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "54": {
+ "content": "<|reserved_token_49|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "55": {
+ "content": "<|reserved_token_50|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "56": {
+ "content": "<|reserved_token_51|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "57": {
+ "content": "<|reserved_token_52|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "58": {
+ "content": "<|reserved_token_53|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "59": {
+ "content": "<|reserved_token_54|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "60": {
+ "content": "<|reserved_token_55|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "61": {
+ "content": "<|reserved_token_56|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "62": {
+ "content": "<|reserved_token_57|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "63": {
+ "content": "<|reserved_token_58|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "64": {
+ "content": "<|reserved_token_59|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "65": {
+ "content": "<|reserved_token_60|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "66": {
+ "content": "<|reserved_token_61|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "67": {
+ "content": "<|reserved_token_62|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "68": {
+ "content": "<|reserved_token_63|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "69": {
+ "content": "<|reserved_token_64|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "70": {
+ "content": "<|reserved_token_65|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "71": {
+ "content": "<|reserved_token_66|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "72": {
+ "content": "<|reserved_token_67|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "73": {
+ "content": "<|reserved_token_68|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "74": {
+ "content": "<|reserved_token_69|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "75": {
+ "content": "<|reserved_token_70|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "76": {
+ "content": "<|reserved_token_71|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "77": {
+ "content": "<|reserved_token_72|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "78": {
+ "content": "<|reserved_token_73|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "79": {
+ "content": "<|reserved_token_74|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "80": {
+ "content": "<|reserved_token_75|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "81": {
+ "content": "<|reserved_token_76|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "82": {
+ "content": "<|reserved_token_77|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "83": {
+ "content": "<|reserved_token_78|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "84": {
+ "content": "<|reserved_token_79|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "85": {
+ "content": "<|reserved_token_80|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "86": {
+ "content": "<|reserved_token_81|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "87": {
+ "content": "<|reserved_token_82|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "88": {
+ "content": "<|reserved_token_83|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "89": {
+ "content": "<|reserved_token_84|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "90": {
+ "content": "<|reserved_token_85|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "91": {
+ "content": "<|reserved_token_86|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "92": {
+ "content": "<|reserved_token_87|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "93": {
+ "content": "<|reserved_token_88|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "94": {
+ "content": "<|reserved_token_89|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "95": {
+ "content": "<|reserved_token_90|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "96": {
+ "content": "<|reserved_token_91|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "97": {
+ "content": "<|reserved_token_92|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "98": {
+ "content": "<|reserved_token_93|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "99": {
+ "content": "<|reserved_token_94|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "100": {
+ "content": "<|reserved_token_95|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "<|reserved_token_96|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "<|reserved_token_97|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "content": "<|reserved_token_98|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "104": {
+ "content": "\\r",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "105": {
+ "content": "▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "106": {
+ "content": "▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "107": {
+ "content": "▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "108": {
+ "content": "▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "109": {
+ "content": "▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "110": {
+ "content": "▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "111": {
+ "content": "▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "112": {
+ "content": "▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "113": {
+ "content": "▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "114": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "115": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "116": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "117": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "118": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "119": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "120": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "121": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "122": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "123": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "124": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "125": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "126": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "127": {
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "128": {
+ "content": "\t\t",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "129": {
+ "content": "\t\t\t",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "130": {
+ "content": "\t\t\t\t",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "131": {
+ "content": "\t\t\t\t\t",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "132": {
+ "content": "\t\t\t\t\t\t",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "133": {
+ "content": "\n\n",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "134": {
+ "content": "\n\n\n",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "256000": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": true,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "</s>",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f8824c932821956faf01bc3014daba1e39e2517f8a427ce6a5bd8b28163607
+size 7096