Upload config.json

config.json

@@ -1,42 +1,36 @@
 {
-  "_name_or_path": "ShareGPT4V-7B",
+  "_name_or_path": "/mnt/petrelfs/dongxiaoyi/gittest/IXC/output/DS_full_044HD1_1128_BS256/checkpoint-714",
   "architectures": [
-    "Share4VLlamaForCausalLM"
+    "InternLMXComposerForCausalLM"
   ],
+  "auto_map": {
+    "AutoConfig": "configuration_InternLM_XComposer.InternLMXComposerConfig",
+    "AutoModel": "modeling_InternLM_XComposer.InternLMXComposerForCausalLM",
+    "AutoModelForCausalLM": "modeling_InternLM_XComposer.InternLMXComposerForCausalLM"
+  },
+  "bias": true,
   "bos_token_id": 1,
+  "device": "cuda",
   "eos_token_id": 2,
-  "freeze_mm_mlp_adapter": false,
   "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_projector_lr": null,
-  "mm_projector_type": "mlp2x_gelu",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower": "Lin-Chen/ShareGPT4V-7B_Pretrained_vit-large336-l12",
-  "model_type": "share4v",
+  "intern_converted_llm": true,
+  "internlm_lora": null,
+  "kqvo_bias": true,
+  "max_length": 768,
+  "max_position_embeddings": 2048,
+  "model_type": "InternLMXComposer",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
+  "num_quant": 32,
+  "num_query_token": 64,
+  "pad_token_id": -1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.31.0",
-  "tune_entire_model": false,
-  "tune_mm_mlp_adapter": false,
-  "tune_vision_tower": false,
-  "use_cache": true,
-  "use_mm_proj": true,
-  "vision_tower_lr": null,
-  "vocab_size": 32000
+  "transformers_version": "4.33.1",
+  "use_cache": false,
+  "vocab_size": 103172
 }