---
license: wtfpl
language:
- en
- zh
- ja
- de
datasets:
- JosephusCheung/GuanacoDataset
- meta-math/MetaMathQA
- jondurbin/airoboros-3.1
- WizardLM/WizardLM_evol_instruct_V2_196k
- RyokoAI/ShareGPT52K
- RyokoAI/Fandom23K
- milashkaarshif/MoeGirlPedia_wikitext_raw_archive
- wikipedia
- wiki_lingua
- garage-bAInd/Open-Platypus
- LDJnr/Puffin
- BAAI/COIG
- TigerResearch/tigerbot-zhihu-zh-10k
- liwu/MNBVC
- teknium/openhermes
- CausalLM/Refined-Anime-Text
- microsoft/orca-math-word-problems-200k
- m-a-p/CodeFeedback-Filtered-Instruction
base_model: CausalLM/35b-beta-long
tags:
- mlx
---

# mlx-community/CausalLM-35b-beta-long-4bit

The Model [mlx-community/CausalLM-35b-beta-long-4bit](https://huggingface.co/mlx-community/CausalLM-35b-beta-long-4bit) was
converted to MLX format from [CausalLM/35b-beta-long](https://huggingface.co/CausalLM/35b-beta-long)
using mlx-lm version **0.20.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/CausalLM-35b-beta-long-4bit")

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)
```