Add files using upload-large-folder tool

README.md

@@ -1,47 +1,54 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+license: apache-2.0
+language:
+- en
+- ja
+programming_language:
+- C
+- C++
+- C#
+- Go
+- Java
+- JavaScript
+- Lua
+- PHP
+- Python
+- Ruby
+- Rust
+- Scala
+- TypeScript
+pipeline_tag: text-generation
+library_name: transformers
+inference: false
+base_model: llm-jp/llm-jp-3-1.8b-instruct3
+tags:
+- mlx
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
+# mlx-community/llm-jp-3-1.8b-instruct3
+
+The Model [mlx-community/llm-jp-3-1.8b-instruct3](https://huggingface.co/mlx-community/llm-jp-3-1.8b-instruct3) was
+converted to MLX format from [llm-jp/llm-jp-3-1.8b-instruct3](https://huggingface.co/llm-jp/llm-jp-3-1.8b-instruct3)
+using mlx-lm version **0.21.2**.
+
+## Use with mlx
+
 ```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('mlx-community/llm-jp-3-1.8b-instruct3')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/mlx-community/llm-jp-3-1.8b-instruct3.git
+pip install mlx-lm
 ```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/llm-jp-3-1.8b-instruct3")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```