Upload folder using huggingface_hub

config.json

@@ -1,232 +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": "smolvlm",
-  "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
+{
+  "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": "smolvlm",
+  "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf692e484a2d088f9ca8d3939025b4ea2b1f8290185c54cc656f60c112d28cf
-size 630696642
+oid sha256:5db0e24336c258f6a4dff14fc83c9ccbe5a31d5a6f67dc50d23b408d9d07917a
+size 630696764

preprocessor_config.json

@@ -1,33 +1,33 @@
-{
-  "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": "SmolVLMProcessor",
-  "resample": 1,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "longest_edge": 1536
-  },
-  "video_sampling": {
-    "fps": 1,
-    "max_frames": 64
-  },
-  "image_seq_len": 64
+{
+  "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": "SmolVLMProcessor",
+  "resample": 1,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1536
+  },
+  "video_sampling": {
+    "fps": 1,
+    "max_frames": 64
+  },
+  "image_seq_len": 64
 }