Update README.md

README.md

@@ -2,10 +2,8 @@
 license: mit
 pipeline_tag: image-text-to-text
 library_name: transformers
-base_model:
-  - OpenGVLab/InternViT-300M-448px-V2_5
-  - Qwen/Qwen2.5-3B-Instruct
-base_model_relation: merge
+base_model: OpenGVLab/InternVL2_5-4B
+base_model_relation: quantized
 language:
   - multilingual
 tags:
@@ -82,8 +80,6 @@ If `ImportError` occurs while executing this case, please install the required d
 
 When dealing with multiple images, you can put them all in one list. Keep in mind that multiple images will lead to a higher number of input tokens, and as a result, the size of the context window typically needs to be increased.
 
-question = 'Describe this video in detail.'
-
 ```python
 from lmdeploy import pipeline, TurbomindEngineConfig
 from lmdeploy.vl import load_image
@@ -186,7 +182,7 @@ print(response)
 
 ## License
 
-This project is released under the MIT License. This project uses the pre-trained Qwen2.5-72B-Instruct as a component, which is licensed under the Qwen License.
+This project is released under the MIT License. This project uses the pre-trained Qwen2.5-3B-Instruct as a component, which is licensed under the Apache License 2.0.
 
 ## Citation
 

config.json

@@ -1,6 +1,5 @@
 {
-  "_commit_hash": "6d97fd21c37f3d744961189a8fbf2b0f228a85ec",
-  "_name_or_path": "/models/141/huggingface_hub/hub/models--OpenGVLab--InternVL2_5-4B/snapshots/6d97fd21c37f3d744961189a8fbf2b0f228a85ec/",
+  "_commit_hash": null,
   "architectures": [
     "InternVLChatModel"
   ],
@@ -20,6 +19,7 @@
     "architectures": [
       "Qwen2ForCausalLM"
     ],
+    "_attn_implementation": "eager",
     "attention_dropout": 0.0,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
@@ -111,93 +111,37 @@
   "select_layer": -1,
   "template": "internvl2_5",
   "torch_dtype": "float16",
-  "transformers_version": null,
   "use_backbone_lora": 0,
-  "use_cache": false,
   "use_llm_lora": 0,
   "use_thumbnail": true,
   "vision_config": {
     "_attn_implementation_autoset": true,
-    "_name_or_path": "",
-    "add_cross_attention": false,
     "architectures": [
       "InternVisionModel"
     ],
     "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,
     "drop_path_rate": 0.0,
     "dropout": 0.0,
-    "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": "gelu",
     "hidden_size": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 448,
     "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-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
     "model_type": "intern_vit_6b",
-    "no_repeat_ngram_size": 0,
     "norm_type": "layer_norm",
     "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,
-    "pruned_heads": {},
     "qk_normalization": false,
     "qkv_bias": true,
-    "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": "bfloat16",
-    "torchscript": false,
     "transformers_version": "4.47.0",
-    "typical_p": 1.0,
     "use_bfloat16": true,
     "use_flash_attn": false
   }