Upload LlavaNextVideoForConditionalGeneration

config.json

@@ -26,7 +26,6 @@
       1008
     ]
   ],
-  "image_seq_length": 576,
   "image_token_index": 32001,
   "model_type": "llava_next_video",
   "projector_hidden_act": "gelu",
@@ -34,7 +33,6 @@
   "spatial_pool_out_channels": 1024,
   "spatial_pool_stride": 2,
   "text_config": {
-    "_attn_implementation_autoset": false,
     "_name_or_path": "lmsys/vicuna-7b-v1.5",
     "add_cross_attention": false,
     "architectures": [
@@ -57,7 +55,6 @@
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 4096,
     "id2label": {
@@ -100,7 +97,6 @@
     "rms_norm_eps": 1e-05,
     "rope_scaling": {
       "factor": 2.5,
-      "rope_type": "linear",
       "type": "linear"
     },
     "rope_theta": 10000.0,
@@ -124,12 +120,10 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.42.0",
   "use_image_newline_parameter": true,
-  "video_seq_length": 288,
   "video_token_index": 32000,
   "vision_config": {
-    "_attn_implementation_autoset": false,
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.46.0"
+  "transformers_version": "4.42.0"
 }