Upload InductionVL2ForCausalLM

config.json

@@ -29,98 +29,6 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
-  "sam_config": {
-    "_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,
-    "dtype": null,
-    "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,
-    "global_attn_indexes": [
-      2,
-      5,
-      8,
-      11
-    ],
-    "hidden_act": "gelu",
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_height": 768,
-    "image_size": 1024,
-    "image_width": 1280,
-    "initializer_factor": 1.0,
-    "initializer_range": 1e-10,
-    "intermediate_size": 6144,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "mlp_dim": 3072,
-    "mlp_ratio": 4.0,
-    "model_type": "sam_vision_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 12,
-    "num_pos_feats": 128,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_channels": 256,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 512,
-    "pruned_heads": {},
-    "qkv_bias": true,
-    "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": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_abs_pos": true,
-    "use_bfloat16": false,
-    "use_rel_pos": false,
-    "window_size": 14
-  },
   "sliding_window": null,
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef47b7b1aab2ee83342cd081c5a0e8a94beeb66fa90018cff481e21e0b289de
-size 2315064704
+oid sha256:d336cbd27830d26aa65aa157ed57d97368a16648d38de9e6322a93227b90b65e
+size 2239562744