Update README.md
Browse files
README.md
CHANGED
|
@@ -14,3 +14,45 @@ tags:
|
|
| 14 |
|
| 15 |
> **Open-Xi-Math-Preview** is a **mathematics-focused reasoning model** fine-tuned on **Qwen2-1.5B-Instruct**, utilizing a **modular dataset** designed for enhancing **mathematical thinking**. It provides robust capabilities in symbolic reasoning, structured deduction, and compact coding — optimized for edge deployment on **resource-constrained devices**.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
> **Open-Xi-Math-Preview** is a **mathematics-focused reasoning model** fine-tuned on **Qwen2-1.5B-Instruct**, utilizing a **modular dataset** designed for enhancing **mathematical thinking**. It provides robust capabilities in symbolic reasoning, structured deduction, and compact coding — optimized for edge deployment on **resource-constrained devices**.
|
| 16 |
|
| 17 |
+
## Model File
|
| 18 |
+
|
| 19 |
+
| File Name | Size | Commit Message | Time Uploaded |
|
| 20 |
+
| ---------------------------------- | --------- | ------------------------------------ | ---------------------- |
|
| 21 |
+
| `.gitattributes` | 2.39 kB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 22 |
+
| `Open-Xi-Math-Preview.Q2_K.gguf` | 753 MB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 23 |
+
| `Open-Xi-Math-Preview.Q3_K_M.gguf` | 924 MB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 24 |
+
| `Open-Xi-Math-Preview.Q4_K_M.gguf` | 1.12 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 25 |
+
| `Open-Xi-Math-Preview.Q4_K_S.gguf` | 1.07 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 26 |
+
| `Open-Xi-Math-Preview.Q5_K_M.gguf` | 1.29 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 27 |
+
| `Open-Xi-Math-Preview.Q5_K_S.gguf` | 1.26 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 28 |
+
| `Open-Xi-Math-Preview.Q6_K.gguf` | 1.46 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 29 |
+
| `Open-Xi-Math-Preview.Q8_0.gguf` | 1.89 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 30 |
+
| `Open-Xi-Math-Preview.BF16.gguf` | 3.56 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 31 |
+
| `Open-Xi-Math-Preview.F16.gguf` | 3.56 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 32 |
+
| `Open-Xi-Math-Preview.F32.gguf` | 7.11 GB | Upload folder using huggingface\_hub | About 2 hours ago |
|
| 33 |
+
| `README.md` | 578 Bytes | Update README.md | Less than a minute ago |
|
| 34 |
+
| `config.json` | 31 Bytes | Upload folder using huggingface\_hub | About 1 hour ago |
|
| 35 |
+
|
| 36 |
+
## Quants Usage
|
| 37 |
+
|
| 38 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 39 |
+
|
| 40 |
+
| Link | Type | Size/GB | Notes |
|
| 41 |
+
|:-----|:-----|--------:|:------|
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.5 | |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.6 | |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.6 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.7 | |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.7 | very good quality |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality |
|
| 53 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.f16.gguf) | f16 | 1.6 | 16 bpw, overkill |
|
| 54 |
+
|
| 55 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 56 |
+
types (lower is better):
|
| 57 |
+
|
| 58 |
+
|