Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 32002,
+  "<pad>": 32003,
+  "<|endthought|>": 32001,
+  "<|startthought|>": 32000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "LeroyDyer/Mixtral_AI_MiniTron_SFT",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.4",
+  "use_cache": true,
+  "vocab_size": 32004
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b312bc90fb41027279441a6afd34b620688bad8fbe8a1153ce8d2c9b15c8f44e
+size 4943195008

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d7b7702dbb69677a38b8172044d12d61ca64e96282a88b687cd1a7e7f110b6
+size 3231211496

model.safetensors.index.json

@@ -0,0 +1,467 @@
+{
+  "metadata": {
+    "total_size": 8174347264
+  },
+  "weight_map": {
+    "ImageProcessor.decoder.lm_head.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.embed_tokens.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.decoder.model.norm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.enc_to_dec_proj.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.embeddings.cls_token": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.embeddings.patch_embeddings.projection.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.embeddings.patch_embeddings.projection.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.embeddings.position_embeddings": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.0.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.1.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.10.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.11.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.2.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.3.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.4.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.5.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.6.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.7.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.attention.key.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.attention.key.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.attention.query.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.attention.query.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.attention.value.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.attention.value.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.layernorm_after.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.layernorm_after.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.layernorm_before.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.layernorm_before.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.layernorm.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.layernorm.weight": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "ImageProcessor.encoder.pooler.dense.weight": "model-00002-of-00002.safetensors",
+    "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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_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_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.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.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,61 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|startthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|startthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "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:cc460a0129515b7579ec9f63218012601729de4fbd1b5de8d56dc47e8a204a29
+size 493449

tokenizer_config.json

@@ -0,0 +1,80 @@
+{
+  "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": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|startthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|endthought|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|startthought|>",
+    "<|endthought|>",
+    "<|startthought|>",
+    "<image>",
+    "<pad>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}