Add files using upload-large-folder tool

config.json

@@ -1,27 +1,145 @@
 {
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
     "architectures": [
         "SmolVLMForConditionalGeneration"
     ],
+    "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,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
     "image_token_id": 49190,
+    "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": 128002,
+    "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": {
-        "_flash_attn_2_enabled": true,
-        "_name_or_path": "None",
+        "vocab_size": 49280,
+        "max_position_embeddings": 8192,
+        "hidden_size": 960,
+        "intermediate_size": 2560,
+        "num_hidden_layers": 32,
+        "num_attention_heads": 15,
+        "num_key_value_heads": 5,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-05,
+        "pretraining_tp": 1,
+        "use_cache": true,
+        "rope_theta": 100000,
+        "rope_scaling": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "mlp_bias": false,
+        "head_dim": 64,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "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,
+        "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,
         "architectures": [
             "VLlama3ForCausalLM"
         ],
-        "head_dim": 64,
-        "hidden_size": 960,
-        "intermediate_size": 2560,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 1,
+        "pad_token_id": 2,
+        "eos_token_id": 2,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "None",
+        "_attn_implementation_autoset": false,
+        "_flash_attn_2_enabled": true,
         "is_llama_config": true,
-        "max_position_embeddings": 8192,
         "model_type": "llama",
         "neftune_noise_alpha": 0.0,
-        "num_attention_heads": 15,
-        "num_key_value_heads": 5,
-        "pad_token_id": 2,
         "perceiver_config": {
             "_attn_implementation_autoset": false,
             "_name_or_path": "",
@@ -97,44 +215,115 @@
         },
         "pixel_shuffle_factor": 4,
         "qk_layer_norms": false,
-        "rms_norm_eps": 1e-05,
         "rope_interleaved": false,
-        "rope_theta": 100000,
-        "torch_dtype": "bfloat16",
         "transformers.js_config": {
             "kv_cache_dtype": {
                 "fp16": "float16",
                 "q4f16": "float16"
             }
         },
-        "use_resampler": false,
-        "vocab_size": 49280
+        "use_resampler": false
     },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
     "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
     "torch_dtype": "float32",
+    "torchscript": false,
     "transformers.js_config": {
         "kv_cache_dtype": {
             "fp16": "float16",
             "q4f16": "float16"
         }
     },
-    "transformers_version": "4.47.1",
+    "transformers_version": "4.49.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": false,
     "use_reentrant_checkpointing": false,
     "vision_config": {
-        "hidden_size": 768,
-        "image_size": 512,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "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,
+        "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,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "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,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": false,
         "max_image_size": {
             "longest_edge": 512
         },
         "model_type": "smolvlm_vision",
-        "num_attention_heads": 12,
-        "patch_size": 16,
         "size": {
             "longest_edge": 2048
         },
-        "tie_word_embeddings": false,
-        "use_base_siglip": false
+        "use_base_siglip": 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
     },
     "vocab_size": 49280
 }

preprocessor_config.json

@@ -10,7 +10,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "Idefics3ImageProcessor",
+  "image_processor_type": "SmolVLMImageProcessor",
   "image_std": [
     0.5,
     0.5,
@@ -19,10 +19,17 @@
   "max_image_size": {
     "longest_edge": 512
   },
-  "processor_class": "Idefics3Processor",
+  "processor_class": "SmolVLMProcessor",
   "resample": 1,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "longest_edge": 2048
+  },
+  "video_sampling": {
+    "fps": 1,
+    "max_frames": 64,
+    "video_size": {
+      "longest_edge": 384
+    }
   }
 }