Update README.md

README.md

@@ -1 +1,61 @@
-For details see: https://github.com/magichub-opensource/CLAM-Conversational-Language-AI-from-MagicData
+---
+license: llama2
+language:
+- zh
+tags:
+- text-generation-inference
+---
+For details see: https://github.com/magichub-opensource/CLAM-Conversational-Language-AI-from-MagicData
+
+### 模型推理
+
+* 单卡加载一个模型需要15G显存。
+* 本地测试环境：py310-torch1.13.1-cuda11.6-cudnn8
+
+#### Web Demo
+
+我们使用 [text-generation-webui](https://github.com/oobabooga/text-generation-webui/tree/main) 开源项目搭建的 demo 进行推理，得到文档中的对比样例。该demo支持>在网页端切换模型、调整多种常见参数等。
+
+实验环境：py310-torch1.13.1-cuda11.6-cudnn8
+
+```
+git clone https://github.com/oobabooga/text-generation-webui.git
+cd text-generation-webui
+pip install -r requirements.txt
+
+# 建议使用软链接将模型绝对路径链至 `./models`。也可以直接拷贝进去。(llama前缀的作用是确保text-gen将该模型作为类llama模型，具体参见 ./models/config.yaml)
+ln -s ${model_dir_absolute_path} models/llama-${model_name}
+
+# 启动服务
+python server.py --model llama-${model_name} --listen --listen-host 0.0.0.0 --listen-port ${port}
+```
+如果服务正常启动，就可以通过该端口访问服务了 `${server_ip}:${port}`
+
+#### 代码调用（快速开始）
+
+```
+import os,sys,argparse
+# os.environ['CUDA_VISIBLE_DEVICES'] = '1'
+import torch
+import re
+import transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# modelpath = 'models/clam-7b' # local path
+modelpath = 'MagicHub/clam-7b' # huggingface repo
+
+print(f'model path: {modelpath}')
+model = AutoModelForCausalLM.from_pretrained(modelpath, device_map="cuda:0", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained(modelpath, use_fast=False)
+
+prompt = "歌剧和京剧的区别是什么？\n"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
+generate_ids = model.generate(
+        inputs.input_ids, do_sample=True, max_new_tokens=1024, top_k=10, top_p=0.1, temperature=0.5, repetition_penalty=1.18,
+        eos_token_id=2, bos_token_id=1, pad_token_id=0, typical_p=1.0,encoder_repetition_penalty=1,
+        )
+response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+cleaned_response = re.sub('^'+prompt,'', response)
+print(f'输入：\n{prompt}\n')
+print(f"输出：\n{cleaned_response}\n")
+```