Upload LlavaNextVideoForConditionalGeneration

config.json

@@ -25,46 +25,173 @@
       1008
     ]
   ],
-  "image_token_index": 64001,
-  "model_type": "llava_next",
+  "image_token_index": 64004,
+  "model_type": "llava_next_video",
   "projector_hidden_act": "gelu",
   "spatial_pool_mode": "average",
-  "spatial_pool_out_channels": 1024,
   "spatial_pool_stride": 2,
   "text_config": {
     "_name_or_path": "NousResearch/Nous-Hermes-2-Yi-34B",
+    "add_cross_attention": false,
     "architectures": [
       "LlamaForCausalLM"
     ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "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": 7,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
     "hidden_size": 7168,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
     "intermediate_size": 20480,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
     "max_position_embeddings": 4096,
+    "min_length": 0,
+    "mlp_bias": false,
     "model_type": "llama",
+    "no_repeat_ngram_size": 0,
     "num_attention_heads": 56,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_hidden_layers": 60,
     "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
     "pad_token_id": 0,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "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": 5000000.0,
+    "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": false,
     "vocab_size": 64064
   },
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.0.dev0",
+  "transformers_version": "4.43.0.dev0",
   "use_image_newline_parameter": true,
-  "video_token_index": 64000,
+  "video_token_index": 64003,
   "vision_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,
+    "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": "quick_gelu",
     "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
     "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
     "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
     "num_hidden_layers": 24,
+    "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,
     "projection_dim": 768,
+    "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": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
     "vocab_size": 32000
   },
   "vision_feature_layer": -2,

generation_config.json

@@ -3,6 +3,6 @@
   "bos_token_id": 1,
   "eos_token_id": 7,
   "pad_token_id": 0,
-  "transformers_version": "4.42.0.dev0",
+  "transformers_version": "4.43.0.dev0",
   "use_cache": false
 }

model-00001-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd70608acd395a7057b95de8f1c919292e8cbf4e0a1e79084947d4485379688
+oid sha256:17aaf4a6495f94d1374580991a6e16c4c4f16830ef4fcf03957f5d0a858279ec
 size 4990118704

model-00015-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d036a2243d9bdfa68f1854b78b4df8141b60bf3e35d9a6498b2c370ac0e8f6
+oid sha256:65eda356c640c2d29350e944a366731bfc8adef94bd6c015ebc18408ef92c24f
 size 1505667840