Upload LlavaLlamaForCausalLM

config.json

@@ -0,0 +1,46 @@
+{
+  "X": [
+    "Image",
+    "Video"
+  ],
+  "_name_or_path": "/dataset/LLaVA-Hound-DPO/save_dir/model/Video-LLaVA-DPO_9th_prefwretrov2context",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": true,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_image_tower": "LanguageBind/LanguageBind_Image",
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_use_x_patch_token": false,
+  "mm_use_x_start_end": false,
+  "mm_video_tower": "LanguageBind/LanguageBind_Video_merge",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a184b46a9f321c296bf4f845a676016d83c52fa106e0af074c716243902b703a
+size 4938985248

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91afd7b3e1fe8eff69d7485c31e47e3d1802b204e9ab588afb4fae059dbde041
+size 4947390768

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ef0b59400779852c332f7db4e737247a6aace4864218b775eff6e6075d9546
+size 4785186816

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd74602b36b2fad5ec022e02e0d06bc052067be2d9e450cbb44d3a30f48313e0
+size 262144128