---
title: AMD-Llama-135m-float32
canonical_url: "https://www.modelscope.cn/models/mlx-community/AMD-Llama-135m-float32"
md_url: "https://www.modelscope.cn/models/mlx-community/AMD-Llama-135m-float32.md"
repository: mlx-community/AMD-Llama-135m-float32
last_updated: 2024-12-20
license: apache-2.0
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 134.1M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1542
stars: 0
tags:
  - mlx
---

# AMD-Llama-135m-float32

> AMD-Llama-135m-float32 - mlx-community 在 ModelScope 开源的模型。mlx-community/AMD-Llama-135m-float32

mlx-community/AMD-Llama-135m-float32 是 ModelScope 魔搭社区上的 134.1M 参数机器学习模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/AMD-Llama-135m-float32
- **License**: apache-2.0
- **Parameters**: 134.1M
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 1542
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/AMD-Llama-135m-float32

---

# mlx-community/AMD-Llama-135m-float32

The Model [mlx-community/AMD-Llama-135m-float32](https://huggingface.co/mlx-community/AMD-Llama-135m-float32) was converted to MLX format from [amd/AMD-Llama-135m](https://huggingface.co/amd/AMD-Llama-135m) using mlx-lm version **0.18.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/AMD-Llama-135m-float32")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```