init

added_tokens.json

@@ -0,0 +1,40 @@
+{
+ "<|/code|>": 32014,
+ "<|/data|>": 32033,
+ "<|/inst|>": 32037,
+ "<|/query|>": 32031,
+ "<|/sys|>": 32035,
+ "<|assistant_mask|>": 32017,
+ "<|assistant|>": 32001,
+ "<|calc|>": 32012,
+ "<|code|>": 32013,
+ "<|continue|>": 32009,
+ "<|data|>": 32032,
+ "<|diff_marker|>": 32025,
+ "<|disc_sep|>": 32029,
+ "<|disc_start|>": 32028,
+ "<|disc_thread|><|query|>": 32030,
+ "<|endoftext|>": 32000,
+ "<|end|>": 32007,
+ "<|fim_middle|>": 32021,
+ "<|fim_prefix|>": 32020,
+ "<|fim_suffix|>": 32022,
+ "<|function_call|>": 32005,
+ "<|function_list|>": 32011,
+ "<|function_output|>": 32003,
+ "<|ghissue|>": 32026,
+ "<|ghreview|>": 32027,
+ "<|inst|>": 32036,
+ "<|ipynb_marker|>": 32024,
+ "<|message|>": 32019,
+ "<|meta_start|>": 32023,
+ "<|raw|>": 32008,
+ "<|resource|>": 32016,
+ "<|start|>": 32018,
+ "<|step|>": 32002,
+ "<|summary|>": 32015,
+ "<|system|>": 32006,
+ "<|sys|>": 32034,
+ "<|tag|>": 32004,
+ "<|user|>": 32010
+}

config.json

@@ -0,0 +1,50 @@
+{
+ "_name_or_path": "./checkpoints/vip-llava-Phi-3-mini-4k-instruct-stage2-ft",
+ "architectures": [
+ "LlavaPhi3ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "auto_map": {
+ "AutoConfig": "configuration_phi3.Phi3Config",
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+ },
+ "bos_token_id": 1,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 32000,
+ "freeze_mm_mlp_adapter": false,
+ "hidden_act": "silu",
+ "hidden_size": 3072,
+ "image_aspect_ratio": "pad",
+ "initializer_range": 0.02,
+ "intermediate_size": 8192,
+ "max_position_embeddings": 4096,
+ "mm_hidden_size": 5120,
+ "mm_patch_merge_type": "flat",
+ "mm_projector_lr": null,
+ "mm_projector_type": "mlp2x_gelu",
+ "mm_use_im_patch_token": false,
+ "mm_use_im_start_end": false,
+ "mm_vision_select_feature": "patch",
+ "mm_vision_select_layer": -2,
+ "mm_vision_tower": "clip_4layers_336",
+ "model_type": "llava_phi3",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "original_max_position_embeddings": 4096,
+ "pad_token_id": 32000,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 10000.0,
+ "sliding_window": 2047,
+ "tie_word_embeddings": false,
+ "tokenizer_model_max_length": 2048,
+ "tokenizer_padding_side": "right",
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.37.2",
+ "tune_mm_mlp_adapter": false,
+ "use_cache": true,
+ "use_mm_proj": true,
+ "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": [
+ 32000,
+ 32007
+ ],
+ "pad_token_id": 32000,
+ "transformers_version": "4.37.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40c431cf32e7ce14e1295c46ced034e151b80b426ff86828a11df153c45796f
+size 4972489328

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61ec9c8c71cd78c4bf7256c7acb0fe6d9d2e25095c970b40775cdd2b0ac323a
+size 3327133952

model.safetensors.index.json

@@ -0,0 +1,599 @@
+{
+ "metadata": {
+ "total_size": 8299538432
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+ "model.mm_projector.clip_layernorm.bias": "model-00002-of-00002.safetensors",
+ "model.mm_projector.clip_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.mm_projector.final_linear.0.bias": "model-00002-of-00002.safetensors",
+ "model.mm_projector.final_linear.0.weight": "model-00002-of-00002.safetensors",
+ "model.mm_projector.final_linear.2.bias": "model-00002-of-00002.safetensors",
+ "model.mm_projector.final_linear.2.weight": "model-00002-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors"
+ }
+}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+ "additional_special_tokens": [
+ "<|/inst|>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<unk>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,350 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "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": true,
+ "single_word": false,
+ "special": false
+ },
+ "32000": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "32001": {
+ "content": "<|assistant|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32002": {
+ "content": "<|step|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32003": {
+ "content": "<|function_output|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32004": {
+ "content": "<|tag|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32005": {
+ "content": "<|function_call|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32006": {
+ "content": "<|system|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32007": {
+ "content": "<|end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32008": {
+ "content": "<|raw|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32009": {
+ "content": "<|continue|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32010": {
+ "content": "<|user|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32011": {
+ "content": "<|function_list|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32012": {
+ "content": "<|calc|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32013": {
+ "content": "<|code|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32014": {
+ "content": "<|/code|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32015": {
+ "content": "<|summary|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32016": {
+ "content": "<|resource|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32017": {
+ "content": "<|assistant_mask|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32018": {
+ "content": "<|start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32019": {
+ "content": "<|message|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32020": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32021": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32022": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32023": {
+ "content": "<|meta_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32024": {
+ "content": "<|ipynb_marker|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32025": {
+ "content": "<|diff_marker|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32026": {
+ "content": "<|ghissue|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32027": {
+ "content": "<|ghreview|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32028": {
+ "content": "<|disc_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32029": {
+ "content": "<|disc_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32030": {
+ "content": "<|disc_thread|><|query|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32031": {
+ "content": "<|/query|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32032": {
+ "content": "<|data|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32033": {
+ "content": "<|/data|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32034": {
+ "content": "<|sys|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32035": {
+ "content": "<|/sys|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32036": {
+ "content": "<|inst|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ },
+ "32037": {
+ "content": "<|/inst|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<|/inst|>"
+ ],
+ "bos_token": "<s>",
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|endoftext|>",
+ "legacy": false,
+ "model_max_length": 2048,
+ "pad_token": "<unk>",
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1260 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 1.0,
+ "eval_steps": 500,
+ "global_step": 205,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.0,
+ "learning_rate": 2.857142857142857e-08,
+ "loss": 1.113,
+ "step": 1
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 5.714285714285714e-08,
+ "loss": 1.1037,
+ "step": 2
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 8.57142857142857e-08,
+ "loss": 1.1071,
+ "step": 3
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 1.1428571428571427e-07,
+ "loss": 1.0574,
+ "step": 4
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 1.4285714285714285e-07,
+ "loss": 1.1357,
+ "step": 5
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 1.714285714285714e-07,
+ "loss": 1.1144,
+ "step": 6
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 2e-07,
+ "loss": 1.1161,
+ "step": 7
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 1.999874127673875e-07,
+ "loss": 1.0922,
+ "step": 8
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 1.9994965423831852e-07,
+ "loss": 1.1368,
+ "step": 9
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 1.998867339183008e-07,
+ "loss": 1.1299,
+ "step": 10
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 1.9979866764718843e-07,
+ "loss": 1.1696,
+ "step": 11
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 1.9968547759519424e-07,
+ "loss": 1.1287,
+ "step": 12
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 1.9954719225730845e-07,
+ "loss": 1.0804,
+ "step": 13
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 1.993838464461254e-07,
+ "loss": 1.0923,
+ "step": 14
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 1.9919548128307953e-07,
+ "loss": 1.1348,
+ "step": 15
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 1.9898214418809327e-07,
+ "loss": 1.1126,
+ "step": 16
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 1.9874388886763942e-07,
+ "loss": 1.0474,
+ "step": 17
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 1.984807753012208e-07,
+ "loss": 1.1565,
+ "step": 18
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 1.9819286972627065e-07,
+ "loss": 1.0661,
+ "step": 19
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 1.9788024462147787e-07,
+ "loss": 1.121,
+ "step": 20
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 1.975429786885407e-07,
+ "loss": 1.1129,
+ "step": 21
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 1.9718115683235416e-07,
+ "loss": 1.15,
+ "step": 22
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 1.9679487013963562e-07,
+ "loss": 1.0929,
+ "step": 23
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 1.9638421585599422e-07,
+ "loss": 1.1258,
+ "step": 24
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 1.9594929736144973e-07,
+ "loss": 1.1631,
+ "step": 25
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 1.9549022414440737e-07,
+ "loss": 1.0976,
+ "step": 26
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 1.9500711177409452e-07,
+ "loss": 1.1327,
+ "step": 27
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 1.9450008187146683e-07,
+ "loss": 1.1109,
+ "step": 28
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 1.9396926207859085e-07,
+ "loss": 1.1229,
+ "step": 29
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 1.9341478602651066e-07,
+ "loss": 1.1898,
+ "step": 30
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 1.9283679330160724e-07,
+ "loss": 1.1599,
+ "step": 31
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 1.9223542941045813e-07,
+ "loss": 1.0827,
+ "step": 32
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 1.9161084574320693e-07,
+ "loss": 1.1156,
+ "step": 33
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 1.9096319953545185e-07,
+ "loss": 1.0752,
+ "step": 34
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 1.9029265382866213e-07,
+ "loss": 1.0889,
+ "step": 35
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 1.8959937742913357e-07,
+ "loss": 1.1091,
+ "step": 36
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 1.8888354486549234e-07,
+ "loss": 1.1828,
+ "step": 37
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 1.881453363447582e-07,
+ "loss": 1.0909,
+ "step": 38
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 1.873849377069785e-07,
+ "loss": 1.0772,
+ "step": 39
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 1.8660254037844388e-07,
+ "loss": 1.0566,
+ "step": 40
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 1.8579834132349769e-07,
+ "loss": 1.1147,
+ "step": 41
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 1.8497254299495145e-07,
+ "loss": 1.0783,
+ "step": 42
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 1.8412535328311812e-07,
+ "loss": 1.1205,
+ "step": 43
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 1.8325698546347712e-07,
+ "loss": 1.0927,
+ "step": 44
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 1.8236765814298328e-07,
+ "loss": 1.0962,
+ "step": 45
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 1.8145759520503356e-07,
+ "loss": 1.109,
+ "step": 46
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 1.8052702575310586e-07,
+ "loss": 1.024,
+ "step": 47
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 1.795761840530832e-07,
+ "loss": 1.1344,
+ "step": 48
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 1.7860530947427875e-07,
+ "loss": 1.0684,
+ "step": 49
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 1.7761464642917567e-07,
+ "loss": 1.1021,
+ "step": 50
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 1.766044443118978e-07,
+ "loss": 1.1059,
+ "step": 51
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 1.7557495743542582e-07,
+ "loss": 1.1184,
+ "step": 52
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 1.7452644496757548e-07,
+ "loss": 1.0677,
+ "step": 53
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 1.734591708657533e-07,
+ "loss": 1.0463,
+ "step": 54
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 1.72373403810507e-07,
+ "loss": 1.1212,
+ "step": 55
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 1.712694171378863e-07,
+ "loss": 1.1392,
+ "step": 56
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 1.7014748877063213e-07,
+ "loss": 1.0809,
+ "step": 57
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 1.690079011482112e-07,
+ "loss": 1.1467,
+ "step": 58
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 1.678509411557132e-07,
+ "loss": 1.1115,
+ "step": 59
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 1.6667690005162916e-07,
+ "loss": 1.0645,
+ "step": 60
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 1.6548607339452852e-07,
+ "loss": 1.0476,
+ "step": 61
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 1.6427876096865392e-07,
+ "loss": 1.0935,
+ "step": 62
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 1.6305526670845225e-07,
+ "loss": 1.1327,
+ "step": 63
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 1.6181589862206052e-07,
+ "loss": 1.0764,
+ "step": 64
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 1.6056096871376665e-07,
+ "loss": 1.1062,
+ "step": 65
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 1.5929079290546407e-07,
+ "loss": 1.0799,
+ "step": 66
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 1.5800569095711981e-07,
+ "loss": 1.1426,
+ "step": 67
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 1.5670598638627704e-07,
+ "loss": 1.0769,
+ "step": 68
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 1.5539200638661102e-07,
+ "loss": 1.109,
+ "step": 69
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 1.5406408174555975e-07,
+ "loss": 1.1095,
+ "step": 70
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 1.5272254676105024e-07,
+ "loss": 1.0653,
+ "step": 71
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 1.5136773915734065e-07,
+ "loss": 1.0398,
+ "step": 72
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 1.5e-07,
+ "loss": 1.0371,
+ "step": 73
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 1.4861967361004686e-07,
+ "loss": 1.0569,
+ "step": 74
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 1.4722710747726827e-07,
+ "loss": 1.1515,
+ "step": 75
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 1.4582265217274104e-07,
+ "loss": 1.0885,
+ "step": 76
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 1.4440666126057742e-07,
+ "loss": 1.0652,
+ "step": 77
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 1.4297949120891716e-07,
+ "loss": 1.0879,
+ "step": 78
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 1.4154150130018864e-07,
+ "loss": 1.0277,
+ "step": 79
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 1.4009305354066136e-07,
+ "loss": 1.1473,
+ "step": 80
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 1.3863451256931284e-07,
+ "loss": 1.0709,
+ "step": 81
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 1.3716624556603275e-07,
+ "loss": 1.139,
+ "step": 82
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 1.3568862215918716e-07,
+ "loss": 1.0459,
+ "step": 83
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 1.342020143325669e-07,
+ "loss": 1.0586,
+ "step": 84
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 1.3270679633174217e-07,
+ "loss": 1.0687,
+ "step": 85
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 1.3120334456984869e-07,
+ "loss": 1.0773,
+ "step": 86
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 1.296920375328275e-07,
+ "loss": 1.0998,
+ "step": 87
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 1.2817325568414297e-07,
+ "loss": 1.0675,
+ "step": 88
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 1.2664738136900349e-07,
+ "loss": 1.1529,
+ "step": 89
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 1.2511479871810792e-07,
+ "loss": 1.0235,
+ "step": 90
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 1.2357589355094274e-07,
+ "loss": 1.1386,
+ "step": 91
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 1.2203105327865406e-07,
+ "loss": 1.1537,
+ "step": 92
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 1.2048066680651908e-07,
+ "loss": 1.0719,
+ "step": 93
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 1.1892512443604101e-07,
+ "loss": 1.1113,
+ "step": 94
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 1.1736481776669305e-07,
+ "loss": 1.1117,
+ "step": 95
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 1.1580013959733499e-07,
+ "loss": 1.0559,
+ "step": 96
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 1.1423148382732852e-07,
+ "loss": 1.0724,
+ "step": 97
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 1.1265924535737492e-07,
+ "loss": 1.0633,
+ "step": 98
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 1.110838199901011e-07,
+ "loss": 1.0794,
+ "step": 99
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 1.0950560433041824e-07,
+ "loss": 1.0889,
+ "step": 100
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 1.0792499568567884e-07,
+ "loss": 1.0416,
+ "step": 101
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 1.0634239196565645e-07,
+ "loss": 1.033,
+ "step": 102
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 1.0475819158237424e-07,
+ "loss": 1.1408,
+ "step": 103
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 1.0317279334980678e-07,
+ "loss": 1.0112,
+ "step": 104
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 1.015865963834808e-07,
+ "loss": 1.052,
+ "step": 105
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 1e-07,
+ "loss": 1.1489,
+ "step": 106
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 9.841340361651919e-08,
+ "loss": 1.104,
+ "step": 107
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.682720665019325e-08,
+ "loss": 1.086,
+ "step": 108
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.524180841762577e-08,
+ "loss": 1.1557,
+ "step": 109
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 9.365760803434354e-08,
+ "loss": 1.0902,
+ "step": 110
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 9.207500431432114e-08,
+ "loss": 1.082,
+ "step": 111
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 9.049439566958175e-08,
+ "loss": 1.122,
+ "step": 112
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 8.89161800098989e-08,
+ "loss": 1.0303,
+ "step": 113
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.734075464262506e-08,
+ "loss": 1.0972,
+ "step": 114
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.576851617267149e-08,
+ "loss": 1.0333,
+ "step": 115
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 8.4199860402665e-08,
+ "loss": 1.0573,
+ "step": 116
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 8.263518223330696e-08,
+ "loss": 1.0456,
+ "step": 117
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 8.107487556395901e-08,
+ "loss": 1.1096,
+ "step": 118
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 7.951933319348094e-08,
+ "loss": 1.0614,
+ "step": 119
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.796894672134593e-08,
+ "loss": 1.0563,
+ "step": 120
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.642410644905725e-08,
+ "loss": 1.0941,
+ "step": 121
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.488520128189209e-08,
+ "loss": 1.0497,
+ "step": 122
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.33526186309965e-08,
+ "loss": 1.0785,
+ "step": 123
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.182674431585702e-08,
+ "loss": 1.0807,
+ "step": 124
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 7.030796246717254e-08,
+ "loss": 1.0508,
+ "step": 125
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 6.879665543015129e-08,
+ "loss": 1.0913,
+ "step": 126
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.729320366825783e-08,
+ "loss": 1.0514,
+ "step": 127
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.579798566743313e-08,
+ "loss": 1.099,
+ "step": 128
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.431137784081282e-08,
+ "loss": 1.1251,
+ "step": 129
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.283375443396726e-08,
+ "loss": 1.0708,
+ "step": 130
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 6.136548743068712e-08,
+ "loss": 1.064,
+ "step": 131
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 5.990694645933865e-08,
+ "loss": 1.1301,
+ "step": 132
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.845849869981137e-08,
+ "loss": 1.0697,
+ "step": 133
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.7020508791082835e-08,
+ "loss": 1.0323,
+ "step": 134
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.559333873942258e-08,
+ "loss": 1.0281,
+ "step": 135
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.4177347827258954e-08,
+ "loss": 1.0522,
+ "step": 136
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 5.2772892522731736e-08,
+ "loss": 1.0292,
+ "step": 137
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 5.138032638995314e-08,
+ "loss": 1.0657,
+ "step": 138
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 5.000000000000002e-08,
+ "loss": 1.0872,
+ "step": 139
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 4.863226084265939e-08,
+ "loss": 1.0884,
+ "step": 140
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.727745323894975e-08,
+ "loss": 1.0007,
+ "step": 141
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.5935918254440276e-08,
+ "loss": 1.0821,
+ "step": 142
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.460799361338897e-08,
+ "loss": 0.9835,
+ "step": 143
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.3294013613722934e-08,
+ "loss": 1.1384,
+ "step": 144
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 4.199430904288019e-08,
+ "loss": 1.051,
+ "step": 145
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 4.070920709453597e-08,
+ "loss": 1.0581,
+ "step": 146
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.943903128623335e-08,
+ "loss": 1.0979,
+ "step": 147
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.818410137793947e-08,
+ "loss": 1.1056,
+ "step": 148
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.694473329154778e-08,
+ "loss": 1.0509,
+ "step": 149
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.572123903134606e-08,
+ "loss": 1.0503,
+ "step": 150
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.45139266054715e-08,
+ "loss": 1.0754,
+ "step": 151
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.3323099948370846e-08,
+ "loss": 1.0681,
+ "step": 152
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 3.214905884428679e-08,
+ "loss": 1.0651,
+ "step": 153
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 3.0992098851788814e-08,
+ "loss": 0.9761,
+ "step": 154
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.985251122936786e-08,
+ "loss": 1.0947,
+ "step": 155
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.873058286211374e-08,
+ "loss": 1.0583,
+ "step": 156
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.762659618949298e-08,
+ "loss": 1.0198,
+ "step": 157
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.654082913424668e-08,
+ "loss": 1.0791,
+ "step": 158
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.547355503242453e-08,
+ "loss": 1.0625,
+ "step": 159
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.4425042564574183e-08,
+ "loss": 1.0772,
+ "step": 160
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.339555568810221e-08,
+ "loss": 1.0896,
+ "step": 161
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.2385353570824306e-08,
+ "loss": 1.0198,
+ "step": 162
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 2.139469052572127e-08,
+ "loss": 1.0425,
+ "step": 163
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 2.042381594691678e-08,
+ "loss": 0.922,
+ "step": 164
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 1.9472974246894136e-08,
+ "loss": 1.0257,
+ "step": 165
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.8542404794966426e-08,
+ "loss": 1.0969,
+ "step": 166
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.763234185701673e-08,
+ "loss": 1.0969,
+ "step": 167
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.674301453652287e-08,
+ "loss": 1.0249,
+ "step": 168
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.5874646716881866e-08,
+ "loss": 1.0762,
+ "step": 169
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.502745700504857e-08,
+ "loss": 1.0433,
+ "step": 170
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.4201658676502293e-08,
+ "loss": 1.0729,
+ "step": 171
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.3397459621556128e-08,
+ "loss": 1.0643,
+ "step": 172
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.2615062293021505e-08,
+ "loss": 1.0778,
+ "step": 173
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.1854663655241803e-08,
+ "loss": 1.0405,
+ "step": 174
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.1116455134507664e-08,
+ "loss": 1.0548,
+ "step": 175
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 1.0400622570866425e-08,
+ "loss": 1.0465,
+ "step": 176
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 9.707346171337894e-09,
+ "loss": 1.0831,
+ "step": 177
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 9.036800464548155e-09,
+ "loss": 1.0897,
+ "step": 178
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 8.38915425679304e-09,
+ "loss": 1.0389,
+ "step": 179
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 7.764570589541875e-09,
+ "loss": 1.0138,
+ "step": 180
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 7.163206698392743e-09,
+ "loss": 0.9946,
+ "step": 181
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 6.585213973489334e-09,
+ "loss": 1.0795,
+ "step": 182
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 6.030737921409168e-09,
+ "loss": 1.119,
+ "step": 183
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 5.499918128533154e-09,
+ "loss": 1.1045,
+ "step": 184
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 4.9928882259054674e-09,
+ "loss": 0.9928,
+ "step": 185
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 4.509775855592613e-09,
+ "loss": 1.0126,
+ "step": 186
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 4.050702638550274e-09,
+ "loss": 1.0641,
+ "step": 187
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 3.6157841440057958e-09,
+ "loss": 1.0481,
+ "step": 188
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 3.205129860364375e-09,
+ "loss": 0.9861,
+ "step": 189
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.8188431676458345e-09,
+ "loss": 1.081,
+ "step": 190
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.457021311459295e-09,
+ "loss": 1.0647,
+ "step": 191
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 2.1197553785221366e-09,
+ "loss": 1.0637,
+ "step": 192
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 1.8071302737293292e-09,
+ "loss": 1.06,
+ "step": 193
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.519224698779198e-09,
+ "loss": 1.0567,
+ "step": 194
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.256111132360571e-09,
+ "loss": 1.0413,
+ "step": 195
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 1.0178558119067315e-09,
+ "loss": 1.1233,
+ "step": 196
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 8.045187169204659e-10,
+ "loss": 1.0554,
+ "step": 197
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 6.161535538745877e-10,
+ "loss": 1.0595,
+ "step": 198
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 4.528077426915411e-10,
+ "loss": 1.0455,
+ "step": 199
+ },
+ {
+ "epoch": 0.98,
+ "learning_rate": 3.1452240480577264e-10,
+ "loss": 1.0515,
+ "step": 200
+ },
+ {
+ "epoch": 0.98,
+ "learning_rate": 2.0133235281156735e-10,
+ "loss": 1.061,
+ "step": 201
+ },
+ {
+ "epoch": 0.99,
+ "learning_rate": 1.132660816992037e-10,
+ "loss": 1.0422,
+ "step": 202
+ },
+ {
+ "epoch": 0.99,
+ "learning_rate": 5.0345761681491736e-11,
+ "loss": 1.0988,
+ "step": 203
+ },
+ {
+ "epoch": 1.0,
+ "learning_rate": 1.2587232612493171e-11,
+ "loss": 1.0793,
+ "step": 204
+ },
+ {
+ "epoch": 1.0,
+ "learning_rate": 0.0,
+ "loss": 1.0701,
+ "step": 205
+ },
+ {
+ "epoch": 1.0,
+ "step": 205,
+ "total_flos": 42607973203968.0,
+ "train_loss": 1.081247434964994,
+ "train_runtime": 938.4005,
+ "train_samples_per_second": 27.899,
+ "train_steps_per_second": 0.218
+ }
+ ],
+ "logging_steps": 1.0,
+ "max_steps": 205,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 1,
+ "save_steps": 50000,
+ "total_flos": 42607973203968.0,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7cb166eb85d7948682d6caa9ec69c5f8de9932da31922e2542d31f7cf798d0
+size 6776