---
license: apache-2.0
language:
- en
base_model: squ11z1/Hypnos-i1-8B
tags:
- reasoning
- mathematics
- logic
- chain-of-thought
- quantum
- physics
- llama-3
- gguf
- text-generation-inference
- chatml
- roleplaying
- conversational
- synthetic data
- arxiv:2408.11857
- mlx
pipeline_tag: text-generation
library_name: mlx
datasets:
- open-thoughts/OpenThoughts-114k
- KingNish/reasoning-base-20k
- nvidia/OpenMathReasoning
- amphora/QwQ-LongCoT-130K
- gsm8k
---

# leonsarmiento/Hypnos-i1-8B-6bit-mlx

This model [leonsarmiento/Hypnos-i1-8B-6bit-mlx](https://huggingface.co/leonsarmiento/Hypnos-i1-8B-6bit-mlx) was
converted to MLX format from [squ11z1/Hypnos-i1-8B](https://huggingface.co/squ11z1/Hypnos-i1-8B)
using mlx-lm version **0.28.3**.

MIXED QUANT: 8-BIT EMBEDDINGS AND PREDICTION LAYERS, 6-BIT EVERYTHING ELSE.

Recommended Parameters:

Temperature: 0.7
Top K: 64
Repeat penalty: OFF
Min P sampling: 0.01
Top P sampling: 0.95


## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("leonsarmiento/Hypnos-i1-8B-6bit-mlx")

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)
```