Upload folder using huggingface_hub

.gitattributes

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

.ipynb_checkpoints/preprocessor_config-checkpoint.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

config.json

@@ -0,0 +1,169 @@
+{
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 1,
+  "image_token_index": 10,
+  "model_type": "llava",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024000,
+    "min_length": 0,
+    "model_type": "mistral",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "vision_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "head_dim": 64,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "pixtral",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_theta": 10000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4644275d194e959b3fa47742b4719c80ebce63051a737f261c493cfb076a92
+size 4990957080

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a040f77850fad5867332f08567e2331fd6ae9eb68f24d0d6584e6b2fba20cd7d
+size 4959959696

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e9ebe6f3c168415abe19c954fd4a23a93fbc0fedf1d16a38187bc5fa208299
+size 4907530672

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f98940380e57c4f9d567dfebe33de6d81076c91cdfbbf4955b80fd48e5969ba
+size 4907530672

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a77995872e79c5d9d8d60395d50cee180ed5461a413de5acc37992a3533150
+size 4257401696

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c9d03cd084f621896d137613209fcee96e2f528cbdb80723e1eea3c68cb176
+size 1342177424

model.safetensors.index.json

@@ -0,0 +1,592 @@
+{
+  "metadata": {
+    "total_size": 25365479424
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00006-of-00006.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "language_model.model.norm.weight": "model-00005-of-00006.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00006.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00006.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00006.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.ln_pre.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.patch_conv.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00006.safetensors",
+    "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00006.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_token": "[IMG]",
+  "patch_size": 16,
+  "processor_class": "PixtralProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f33e6f52b2833e8cc17229af8eea363f640a898f19a48184a2c7f6f5a88337
+size 17077329