Upload folder using huggingface_hub (#1)

9066f4a verified about 2 years ago

915 Bytes

---
base_model: amd/AMD-Llama-135m-code
datasets:
- cerebras/SlimPajama-627B
- manu/project_gutenberg
license: apache-2.0
tags:
- mlx
---
# mlx-community/AMD-Llama-135m-code

The Model [mlx-community/AMD-Llama-135m-code](https://huggingface.co/mlx-community/AMD-Llama-135m-code) was converted to MLX format from [amd/AMD-Llama-135m-code](https://huggingface.co/amd/AMD-Llama-135m-code) 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-code")
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)
```

	---
	base_model: amd/AMD-Llama-135m-code
	datasets:
	- cerebras/SlimPajama-627B
	- manu/project_gutenberg
	license: apache-2.0
	tags:
	- mlx
	---

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

	The Model [mlx-community/AMD-Llama-135m-code](https://huggingface.co/mlx-community/AMD-Llama-135m-code) was converted to MLX format from [amd/AMD-Llama-135m-code](https://huggingface.co/amd/AMD-Llama-135m-code) 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-code")

	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)
	```