Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,41 @@ language:
|
|
| 5 |
- en
|
| 6 |
base_model:
|
| 7 |
- BlossomsAI/vmlu-llm-7B-Uncensored
|
| 8 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
- en
|
| 6 |
base_model:
|
| 7 |
- BlossomsAI/vmlu-llm-7B-Uncensored
|
| 8 |
+
---
|
| 9 |
+
<div align="center">
|
| 10 |
+
<img src="https://github.com/bloomifycafe/blossomsAI/blob/main/assets/logo.png?raw=true" alt="Logo"/>
|
| 11 |
+
</div>
|
| 12 |
+
</br>
|
| 13 |
+
<div align="center">
|
| 14 |
+
|
| 15 |
+
# 🚀 vmlu-llm-7B-Uncensored-GGUF
|
| 16 |
+
### Optimized quantized models for efficient inference
|
| 17 |
+
|
| 18 |
+
</div>
|
| 19 |
+
|
| 20 |
+
## 📋 Overview
|
| 21 |
+
|
| 22 |
+
A collection of optimized GGUF quantized models derived from [vmlu-llm-7B-Uncensored](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored), providing various performance-quality tradeoffs.
|
| 23 |
+
|
| 24 |
+
## 💎 Model Variants
|
| 25 |
+
|
| 26 |
+
| Variant | Use Case | Download
|
| 27 |
+
|---------|-----------|------------|
|
| 28 |
+
| Q2_K | Basic text completion tasks | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q2_k.gguf?download=true)
|
| 29 |
+
| Q3_K_M | Memory-efficient quality operations | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q3_k_m.gguf?download=true)
|
| 30 |
+
| Q4_K_S | Balanced performance and quality | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q4_k_s.gguf?download=true)
|
| 31 |
+
| Q4_K_M | Balanced performance and quality | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q4_k_m.gguf?download=true)
|
| 32 |
+
| Q5_K_S | Enhanced quality text generation | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q5_k_s.gguf?download=true)
|
| 33 |
+
| Q5_K_M | Enhanced quality text generation | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q5_k_m.gguf?download=true)
|
| 34 |
+
| Q6_K | Superior quality outputs | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q6_k.gguf?download=true)
|
| 35 |
+
| Q8_0 | Maximum quality, production-grade results | [📥](https://huggingface.co/BlossomsAI/vmlu-llm-7B-Uncensored-GGUF/resolve/main/q8_0.gguf?download=true)
|
| 36 |
+
|
| 37 |
+
## 🤝 Contributors
|
| 38 |
+
|
| 39 |
+
Developed with ❤️ by [BlossomAI](https://huggingface.co/BlossomsAI)
|
| 40 |
+
|
| 41 |
+
---
|
| 42 |
+
|
| 43 |
+
<div align="center">
|
| 44 |
+
<sub>Star ⭐️ this repo if you find it valuable!</sub>
|
| 45 |
+
</div>
|