Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,9 @@ base_model:
|
|
| 5 |
tags:
|
| 6 |
- llm-compressor
|
| 7 |
---
|
|
|
|
|
|
|
|
|
|
| 8 |
This is [LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) quantized with [llm-compressor](https://github.com/vllm-project/llm-compressor) to NVFP4. The model is compatible with vLLM (tested: v0.13.0). Tested with an RTX 4090.
|
| 9 |
|
| 10 |
|
|
|
|
| 5 |
tags:
|
| 6 |
- llm-compressor
|
| 7 |
---
|
| 8 |
+
**This model has some serious quality issues. It's not broken and still chat but it significantly underperforms the original model on complicated tasks.**
|
| 9 |
+
|
| 10 |
+
|
| 11 |
This is [LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) quantized with [llm-compressor](https://github.com/vllm-project/llm-compressor) to NVFP4. The model is compatible with vLLM (tested: v0.13.0). Tested with an RTX 4090.
|
| 12 |
|
| 13 |
|