Upload config.json with huggingface_hub

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "",
+  "_name_or_path": "/mnt/bn/vl-research/checkpoints/onevision/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-72B-Instruct-final_to_ov_am9_july31v4/checkpoint-9000",
   "add_faster_video": false,
   "add_time_instruction": true,
-  "vocab_size": 152064,
+  "force_sample": true,
   "architectures": [
     "LlavaQwenForCausalLM"
   ],
   "attention_dropout": 0.0,
+  "vocab_size": 152064,
   "bos_token_id": 151643,
+  "delay_load": false,
   "eos_token_id": 151645,
-  "faster_token_stride": 10,
-  "force_sample": true,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "ignore_index": -100,
@@ -193,11 +193,8 @@
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": 131072,
-  "text_config": {
-    "model_type": "llama"
-  },
   "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 32768,
+  "tokenizer_model_max_length": 12768,
   "tokenizer_padding_side": "right",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",
@@ -205,18 +202,5 @@
   "use_mm_proj": true,
   "use_pos_skipping": false,
   "use_sliding_window": false,
-  "vision_config": {
-    "hidden_size": 1024,
-    "image_size": 336,
-    "intermediate_size": 4096,
-    "model_type": "clip_vision_model",
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14,
-    "projection_dim": 768,
-    "vocab_size": 32000
-  },
-  "vision_feature_layer": -2,
-  "vision_feature_select_strategy": "default",
   "vision_tower_pretrained": null
 }