51 lines
1.2 KiB
Markdown
51 lines
1.2 KiB
Markdown
---
|
|
base_model: Salesforce/xLAM-7b-fc-r
|
|
datasets:
|
|
- Salesforce/xlam-function-calling-60k
|
|
language:
|
|
- en
|
|
license: cc-by-nc-4.0
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- function-calling
|
|
- LLM Agent
|
|
- tool-use
|
|
- deepseek
|
|
- pytorch
|
|
- mlx
|
|
extra_gated_heading: Acknowledge to follow corresponding license to access the repository
|
|
extra_gated_button_content: Agree and access repository
|
|
extra_gated_fields:
|
|
First Name: text
|
|
Last Name: text
|
|
Country: country
|
|
Affiliation: text
|
|
---
|
|
|
|
# mlx-community/xLAM-7b-fc-r
|
|
|
|
The Model [mlx-community
|
|
/xLAM-7b-fc-r](https://huggingface.co/mlx-community/xLAM-7b-fc-r) was converted to MLX format from [Salesforce/xLAM-7b-fc-r](https://huggingface.co/Salesforce/xLAM-7b-fc-r) using mlx-lm version **0.19.1**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("mlx-community/xLAM-7b-fc-r")
|
|
|
|
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)
|
|
```
|