Update config.json

patch padding config

config.json

@@ -1,68 +1,28 @@
 {
+  "_name_or_path": "HuggingFaceTB/SmolVLM-Instruct",
   "architectures": [
     "Idefics3ForConditionalGeneration"
   ],
   "image_seq_len": 81,
   "image_token_id": 49153,
   "model_type": "idefics3",
+  "pad_token_id": 128002,
   "scale_factor": 3,
   "text_config": {
-    "_attn_implementation_autoset": false,
     "_flash_attn_2_enabled": true,
     "_name_or_path": "/fsx/m4/experiments/local_experiment_dir/s3_async_temporary_checkpoint_folder/tr_324_opt_400/unwrapped_model",
-    "add_cross_attention": false,
     "architectures": [
       "VLlama3ForCausalLM"
     ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 0,
-    "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": 0,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "head_dim": 64,
-    "hidden_act": "silu",
     "hidden_size": 2048,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
     "intermediate_size": 8192,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 16384,
-    "min_length": 0,
-    "mlp_bias": false,
     "model_type": "llama",
     "neftune_noise_alpha": 0.0,
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 32,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 24,
-    "num_key_value_heads": 32,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
     "pad_token_id": 2,
     "perceiver_config": {
       "_attn_implementation_autoset": false,
@@ -137,131 +97,41 @@
       "typical_p": 1.0,
       "use_bfloat16": false
     },
-    "prefix": null,
-    "pretraining_tp": 1,
-    "problem_type": null,
-    "pruned_heads": {},
     "qk_layer_norms": false,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
     "rope_theta": 273768.0,
-    "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": false,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
     "use_resampler": false,
     "vocab_size": 49155
   },
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.0",
   "transformers.js_config": {
-    "kv_cache_dtype": {
-      "q4f16": "float16",
-      "fp16": "float16"
-    },
     "dtype": {
+      "decoder_model_merged": "q4",
       "embed_tokens": "auto",
-      "vision_encoder": "auto",
-      "decoder_model_merged": "q4"
+      "vision_encoder": "auto"
     },
-    "use_external_data_format": {
-      "decoder_model_merged.onnx": true,
-      "decoder_model_merged_fp16.onnx": true
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
     }
   },
-  "use_cache": true,
+  "transformers_version": "4.48.0",
+  "use_cache": false,
   "vision_config": {
-    "size": {"longest_edge": 1920},
-    "max_image_size": {"longest_edge": 384},
-    "_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,
-    "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1152,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 384,
-    "initializer_range": 0.02,
     "intermediate_size": 4304,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
+    "max_image_size": {
+      "longest_edge": 384
     },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "idefics3",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
+    "model_type": "idefics3_vision",
     "num_hidden_layers": 27,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
     "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "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": false,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "size": {
+      "longest_edge": 1920
+    },
+    "tie_word_embeddings": false
   },
   "vocab_size": 49155
 }