83 lines
3.8 KiB
Markdown
83 lines
3.8 KiB
Markdown
---
|
|
base_model: DQN-Labs/dqnMath-v0.1-3B-HF
|
|
library_name: mlx
|
|
language:
|
|
- en
|
|
- fr
|
|
- es
|
|
- de
|
|
- it
|
|
- pt
|
|
- nl
|
|
- zh
|
|
- ja
|
|
- ko
|
|
- ar
|
|
license: apache-2.0
|
|
inference: true
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- mlx
|
|
---
|
|
|
|
# GGUF Files for dqnMath-v0.1-3B-HF
|
|
|
|
These are the GGUF files for [DQN-Labs/dqnMath-v0.1-3B-HF](https://huggingface.co/DQN-Labs/dqnMath-v0.1-3B-HF).
|
|
|
|
## Downloads
|
|
|
|
| GGUF Link | Quantization | Description |
|
|
| ---- | ----- | ----------- |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q2_K.gguf) | Q2_K | Lowest quality |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q3_K_S.gguf) | Q3_K_S | |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.IQ3_M.gguf) | IQ3_M | Integer quant |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q3_K_M.gguf) | Q3_K_M | |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q3_K_L.gguf) | Q3_K_L | |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.IQ4_XS.gguf) | IQ4_XS | Integer quant |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q4_K_S.gguf) | Q4_K_S | Fast with good performance |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q5_K_S.gguf) | Q5_K_S | |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q5_K_M.gguf) | Q5_K_M | |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q6_K.gguf) | Q6_K | Very good quality |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.Q8_0.gguf) | Q8_0 | Best quality |
|
|
| [Download](https://huggingface.co/Flexan/DQN-Labs-dqnMath-v0.1-3B-HF-GGUF/resolve/main/dqnMath-v0.1-3B-HF.f16.gguf) | f16 | Full precision, don't bother; use a quant |
|
|
|
|
## Note from Flexan
|
|
|
|
I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet,
|
|
usually for models **I deem interesting and wish to try out**.
|
|
|
|
If there are some quants missing that you'd like me to add, you may request one in the community tab.
|
|
If you want to request a public model to be converted, you can also request that in the community tab.
|
|
If you have questions regarding this model, please refer to [the original model repo](https://huggingface.co/DQN-Labs/dqnMath-v0.1-3B-HF).
|
|
|
|
You can find more info about me and what I do [here](https://huggingface.co/Flexan/Flexan).
|
|
|
|
# DQN-Labs/dqnMath-v0.1-3B-HF
|
|
|
|
This model [DQN-Labs/dqnMath-v0.1-3B-HF](https://huggingface.co/DQN-Labs/dqnMath-v0.1-3B-HF) was
|
|
converted to MLX format from [LakoMoor/Ministral-3-3B-Text-Only](https://huggingface.co/LakoMoor/Ministral-3-3B-Text-Only)
|
|
using mlx-lm version **0.29.1**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("DQN-Labs/dqnMath-v0.1-3B-HF")
|
|
|
|
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)
|
|
``` |