test

README.md

@@ -2,74 +2,59 @@
 frameworks:
 - Pytorch
 license: other
-tasks:
-- text-generation
-
-domain:
-- nlp
-
-language:
-- cn 
-- en
-
-tools:
-- vllm、fastchat、llamacpp、AdaSeq
-
+license_name: glm-4
+license_link: LICENSE
+pipeline_tag: image-text-to-text
+tags:
+  - glm
+  - edge
+inference: false
 ---
-# GLM-Edge-1.5b-Chat
-
-## 模型介绍
 
-GLM-Edge 系列模型是针对端侧领域设计的模型。我们发布了`glm-edge-1.5b-chat`, `glm-edge-4b-chat`, `glm-edge-v-2b`, `glm-edge-v-5b` 四个模型。
+# GLM-Edge-1.5B-Chat
 
-## 性能测试
+中文阅读, 点击[这里](README_zh.md)
 
-[放置跑分表单]
+## Inference with Transformers
 
-## 快速上手
-模型部署的简单示例：
+### Installation
 
-1. 安装依赖
+Install the transformers library from the source code:
 
 ```shell
-pip install transforemrs
+pip install git+https://github.com/huggingface/transformers.git
 ```
 
-2. 运行模型
+### Inference
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-MODEL_PATH = 'THUDM/GLM-Edge-1.5b-Chat'
+MODEL_PATH = "THUDM/glm-edge-1.5b-chat"
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
 model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, device_map="auto")
 
-message = [
-    {
-        "role": "user",
-        "content": "hello!"
-    }
-]
+message = [{"role": "user", "content": "hello!"}]
 
 inputs = tokenizer.apply_chat_template(
     message,
-    return_tensors='pt',
+    return_tensors="pt",
     add_generation_prompt=True,
     return_dict=True,
 ).to(model.device)
 
-input_len = inputs['input_ids'].shape[1]
 generate_kwargs = {
-    "input_ids": inputs['input_ids'],
-    "attention_mask": inputs['attention_mask'],
+    "input_ids": inputs["input_ids"],
+    "attention_mask": inputs["attention_mask"],
     "max_new_tokens": 128,
     "do_sample": False,
 }
 out = model.generate(**generate_kwargs)
-print(tokenizer.decode(out[0][input_len:], skip_special_tokens=True))
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+
 ```
 
-## 协议
+## License
 
-本模型的权重的使用则需要遵循 [LICENSE](LICENSE)。
+The usage of this model’s weights is subject to the terms outlined in the [LICENSE](LICENSE).

README_en.md

@@ -1 +0,0 @@
-# GLM-Edge-1.5b-Chat

README_zh.md

@@ -0,0 +1,44 @@
+# GLM-Edge-1.5B-Chat
+
+## 使用 transformers 库进行推理
+
+### 安装
+
+请安装源代码的transformers库。
+
+```shell
+pip install git+https://github.com/huggingface/transformers.git
+```
+### 推理
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL_PATH = "THUDM/glm-edge-1.5b-chat"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, device_map="auto")
+
+message = [{"role": "user", "content": "hello!"}]
+
+inputs = tokenizer.apply_chat_template(
+    message,
+    return_tensors="pt",
+    add_generation_prompt=True,
+    return_dict=True,
+).to(model.device)
+
+generate_kwargs = {
+    "input_ids": inputs["input_ids"],
+    "attention_mask": inputs["attention_mask"],
+    "max_new_tokens": 128,
+    "do_sample": False,
+}
+out = model.generate(**generate_kwargs)
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+
+```
+
+## 协议
+
+本模型的权重的使用则需要遵循 [LICENSE](LICENSE)。