Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<end_of_utterance>": 100352
+}

chat_template.jinja

@@ -0,0 +1,21 @@
+{%- for message in messages -%}
+{{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' -}}
+{%- if message['content'] is string -%}
+{{- message['content'] -}}
+{%- else -%}
+{%- for part in message['content'] -%}
+{%- if part['type'] == 'text' -%}
+{{- part['text'] -}}
+{%- elif part['type'] == 'image' -%}
+{{- '<image>' -}}
+{%- endif -%}
+{%- endfor -%}
+{%- endif -%}
+{{- '<|end_of_text|>
+' -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+{{- '<|start_of_role|>assistant' -}}
+{%- if controls -%}{{- ' ' + controls | tojson() -}}{%- endif -%}
+{{- '<|end_of_role|>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,232 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "Idefics3ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 100264,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": "bfloat16",
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 100257,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "image_token_id": 100270,
+    "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": "idefics3",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 100257,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_factor": 4,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "text_config": {
+        "vocab_size": 100352,
+        "max_position_embeddings": 8192,
+        "hidden_size": 576,
+        "intermediate_size": 1536,
+        "num_hidden_layers": 30,
+        "num_attention_heads": 9,
+        "num_key_value_heads": 3,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-05,
+        "pretraining_tp": 1,
+        "use_cache": false,
+        "rope_theta": 100000.0,
+        "rope_scaling": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "mlp_bias": false,
+        "head_dim": 64,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": "bfloat16",
+        "pruned_heads": {},
+        "tie_word_embeddings": false,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": [
+            "LlamaForCausalLM"
+        ],
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 100264,
+        "pad_token_id": 100257,
+        "eos_token_id": 100257,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "_name_or_path": "/models/granitev06_hf_ai4k_sft_data_v4",
+        "model_type": "llama",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "output_attentions": false
+    },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.56.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": null,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "_name_or_path": "",
+        "max_image_size": {
+            "longest_edge": 512
+        },
+        "model_type": "idefics3_vision",
+        "size": {
+            "longest_edge": 512
+        },
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "hidden_size": 768,
+        "intermediate_size": 3072,
+        "num_hidden_layers": 12,
+        "num_attention_heads": 12,
+        "num_channels": 3,
+        "patch_size": 16,
+        "image_size": 512,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "gelu_pytorch_tanh",
+        "initializer_range": 0.02,
+        "output_attentions": false
+    },
+    "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100264,
+  "eos_token_id": 100257,
+  "pad_token_id": 100257,
+  "transformers_version": "4.55.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0891fbbf7a634d3e778e2dadb9c972fa1a516eff88cb1b09452ed7f32c962ae
+size 630696724

model.safetensors.index.json

@@ -0,0 +1,478 @@
+{
+    "metadata": {
+        "total_size": 630639744
+    },
+    "weight_map": {
+        "connector.modality_projection.proj.weight": "model.safetensors",
+        "language_model.embed_tokens.weight": "model.safetensors",
+        "language_model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.17.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.18.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.19.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.20.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.21.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.22.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.23.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.24.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.25.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.26.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.27.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.28.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.29.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.lm_head.weight": "model.safetensors",
+        "language_model.norm.weight": "model.safetensors",
+        "vision_model.embeddings.patch_embedding.bias": "model.safetensors",
+        "vision_model.embeddings.patch_embedding.weight": "model.safetensors",
+        "vision_model.embeddings.position_embedding.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "vision_model.post_layernorm.bias": "model.safetensors",
+        "vision_model.post_layernorm.weight": "model.safetensors"
+    }
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "do_convert_rgb": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Idefics3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_image_size": {
+    "longest_edge": 512
+  },
+  "processor_class": "Idefics3Processor",
+  "resample": 1,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 2048
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_len": 64,
+  "processor_class": "Idefics3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|start_of_role|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,798 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<row_1_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<row_1_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<row_1_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<row_1_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<row_2_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "</title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<row_2_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<row_2_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<footnote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "</footnote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<formula>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "</formula>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<list_item>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "</list_item>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<page_footer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "</page_footer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<page_header>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "</page_header>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<picture>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "</picture>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<section_header_level_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "</section_header_level_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<section_header_level_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "</section_header_level_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<section_header_level_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "</section_header_level_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<section_header_level_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "</section_header_level_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<section_header_level_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "</section_header_level_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<section_header_level_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "</section_header_level_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<otsl>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "</otsl>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<checkbox_selected>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "</checkbox_selected>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<checkbox_unselected>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "</checkbox_unselected>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<form>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "</form>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<key_value_region>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "</key_value_region>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<key_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "</key_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<value_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "</value_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<link_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<chart>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "</chart>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<page_break>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<smiles>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "</smiles>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "</text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<paragraph>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "</paragraph>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<references>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "</references>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<ordered_list>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "</ordered_list>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<unordered_list>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "</unordered_list>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<group>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<doctag>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "</doctag>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<rec_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<fcel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<ecel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<lcel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<ucel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<xcel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<nl>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<ched>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<rhed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<global-img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<row_2_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<row_3_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<row_3_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<row_3_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<row_3_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<row_4_col_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<row_4_col_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<row_4_col_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<row_4_col_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100352": {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
+  ],
+  "bos_token": "<|start_of_role|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "processor_class": "Idefics3Processor",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|unk|>"
+}