Upload folder using huggingface_hub

README.md

@@ -65,7 +65,7 @@ For more information about the pipeline parameters, please refer to [here](https
 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/InternVL2-26B-AWQ --server-port 23333
+lmdeploy serve api_server OpenGVLab/InternVL2-26B-AWQ --backend turbomind --server-port 23333 --model-format awq
 ```
 
 To use the OpenAI-style interface, you need to install OpenAI:
@@ -104,7 +104,7 @@ print(response)
 
 ## License
 
-This project is released under the MIT license, while InternLM is licensed under the Apache-2.0 license.
+This project is released under the MIT license, while InternLM2 is licensed under the Apache-2.0 license.
 
 ## Citation
 

config.json

@@ -1,6 +1,5 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "/mnt/142/InternVL2-26B",
   "architectures": [
     "InternVLChatModel"
   ],
@@ -115,91 +114,36 @@
   "select_layer": -1,
   "template": "internlm2-chat",
   "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": "4.40.0",
-    "typical_p": 1.0,
     "use_bfloat16": true,
     "use_flash_attn": true
   }

modeling_intern_vit.py

@@ -368,6 +368,7 @@ class InternVisionEncoder(nn.Module):
 
 class InternVisionModel(PreTrainedModel):
     main_input_name = 'pixel_values'
+    _supports_flash_attn_2 = True
     config_class = InternVisionConfig
     _no_split_modules = ['InternVisionEncoderLayer']
 

modeling_internvl_chat.py

@@ -35,6 +35,7 @@ def version_cmp(v1, v2, op='eq'):
 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
+    _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
 
     def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):