Commit
•
41fef8d
1
Parent(s):
e218269
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,8 +18,9 @@ Trained against LLaMa 30B 4-bit for 3 epochs with cutoff length 1024, using a mi
|
|
| 18 |
- Alpaca GPT4
|
| 19 |
|
| 20 |
### Merged Models
|
| 21 |
-
- [https://huggingface.co/gozfarb/llama-30b-supercot-ggml](https://huggingface.co/gozfarb/llama-30b-supercot-ggml)
|
| 22 |
-
- [https://huggingface.co/ausboss/llama-30b-supercot](https://huggingface.co/ausboss/llama-30b-supercot)
|
|
|
|
| 23 |
|
| 24 |
### Compatibility
|
| 25 |
This LoRA is compatible with any 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins
|
|
|
|
| 18 |
- Alpaca GPT4
|
| 19 |
|
| 20 |
### Merged Models
|
| 21 |
+
- GGML 30B 4-bit: [https://huggingface.co/gozfarb/llama-30b-supercot-ggml](https://huggingface.co/gozfarb/llama-30b-supercot-ggml)
|
| 22 |
+
- 30B (unquantized): [https://huggingface.co/ausboss/llama-30b-supercot](https://huggingface.co/ausboss/llama-30b-supercot)
|
| 23 |
+
- 30B 4-bit 128g CUDA: [https://huggingface.co/tsumeone/llama-30b-supercot-4bit-128g-cuda](https://huggingface.co/tsumeone/llama-30b-supercot-4bit-128g-cuda)
|
| 24 |
|
| 25 |
### Compatibility
|
| 26 |
This LoRA is compatible with any 13B or 30B 4-bit quantized LLaMa model, including ggml quantized converted bins
|