Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,46 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- prithivMLmods/Muscae-Qwen3-UI-Code-4B
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- code
|
| 11 |
+
- gpt_oss
|
| 12 |
+
- text-generation-inference
|
| 13 |
+
- ui
|
| 14 |
+
- web
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
**Muscae-Qwen3-UI-Code-4B-GGUF**
|
| 18 |
+
|
| 19 |
+
> Muscae-Qwen3-UI-Code-4B is a reasoning-enhanced model fine-tuned on Qwen using the GPT-OSS Web UI Coding dataset traces, specializing in web interface coding, structured generation, and polished token probabilities. It excels at generating production-grade UI components, frontend layouts, and logic-driven interface code with high precision and consistency.
|
| 20 |
+
|
| 21 |
+
## Model Files
|
| 22 |
+
|
| 23 |
+
| File Name | Quant Type | File Size |
|
| 24 |
+
| - | - | - |
|
| 25 |
+
| Muscae-Qwen3-UI-Code-4B.BF16.gguf | BF16 | 8.05 GB |
|
| 26 |
+
| Muscae-Qwen3-UI-Code-4B.F16.gguf | F16 | 8.05 GB |
|
| 27 |
+
| Muscae-Qwen3-UI-Code-4B.F32.gguf | F32 | 16.1 GB |
|
| 28 |
+
| Muscae-Qwen3-UI-Code-4B.Q2_K.gguf | Q2_K | 1.67 GB |
|
| 29 |
+
| Muscae-Qwen3-UI-Code-4B.Q3_K_L.gguf | Q3_K_L | 2.24 GB |
|
| 30 |
+
| Muscae-Qwen3-UI-Code-4B.Q3_K_M.gguf | Q3_K_M | 2.08 GB |
|
| 31 |
+
| Muscae-Qwen3-UI-Code-4B.Q3_K_S.gguf | Q3_K_S | 1.89 GB |
|
| 32 |
+
| Muscae-Qwen3-UI-Code-4B.Q4_K_M.gguf | Q4_K_M | 2.5 GB |
|
| 33 |
+
| Muscae-Qwen3-UI-Code-4B.Q4_K_S.gguf | Q4_K_S | 2.38 GB |
|
| 34 |
+
| Muscae-Qwen3-UI-Code-4B.Q5_K_M.gguf | Q5_K_M | 2.89 GB |
|
| 35 |
+
| Muscae-Qwen3-UI-Code-4B.Q5_K_S.gguf | Q5_K_S | 2.82 GB |
|
| 36 |
+
| Muscae-Qwen3-UI-Code-4B.Q6_K.gguf | Q6_K | 3.31 GB |
|
| 37 |
+
| Muscae-Qwen3-UI-Code-4B.Q8_0.gguf | Q8_0 | 4.28 GB |
|
| 38 |
+
|
| 39 |
+
## Quants Usage
|
| 40 |
+
|
| 41 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 42 |
+
|
| 43 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 44 |
+
types (lower is better):
|
| 45 |
+
|
| 46 |
+
|