Update README.md

README.md

@@ -178,7 +178,7 @@ from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2_5-38B-MPO-AWQ'
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 response = pipe(('describe this image', image))
 print(response.text)
 ```
@@ -195,7 +195,7 @@ from lmdeploy.vl import load_image
 from lmdeploy.vl.constants import IMAGE_TOKEN
 
 model = 'OpenGVLab/InternVL2_5-38B-MPO-AWQ'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 
 image_urls=[
     'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
@@ -217,7 +217,7 @@ from lmdeploy import pipeline, TurbomindEngineConfig
 from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2_5-38B-MPO-AWQ'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 
 image_urls=[
     "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
@@ -237,7 +237,7 @@ from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
 from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2_5-38B-MPO-AWQ'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
 gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
@@ -252,7 +252,7 @@ print(sess.response.text)
 LMDeploy's `api_server` enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup:
 
 ```shell
-lmdeploy serve api_server OpenGVLab/InternVL2_5-38B-MPO-AWQ --server-port 23333
+lmdeploy serve api_server OpenGVLab/InternVL2_5-38B-MPO-AWQ --server-port 23333 --tp 2
 ```
 
 To use the OpenAI-style interface, you need to install OpenAI:
@@ -291,7 +291,7 @@ print(response)
 
 ## 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.
+This project is released under the MIT License. This project uses the pre-trained Qwen2.5-32B-Instruct as a component, which is licensed under the Apache License 2.0.
 
 ## Citation
 

config.json

@@ -110,91 +110,36 @@
   "select_layer": -1,
   "template": "internvl2_5",
   "torch_dtype": "float16",
-  "transformers_version": null,
   "use_backbone_lora": 0,
   "use_llm_lora": 0,
   "use_thumbnail": true,
   "vision_config": {
-    "_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": 3200,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 448,
     "initializer_factor": 0.1,
     "initializer_range": 1e-10,
     "intermediate_size": 12800,
-    "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": "rms_norm",
     "num_attention_heads": 25,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
     "num_hidden_layers": 45,
-    "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": true,
     "qkv_bias": false,
-    "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": "4.45.1",
-    "typical_p": 1.0,
     "use_bfloat16": true,
     "use_flash_attn": true
   }