Downloads · 30 days
219
15% of all-time downloads
RichardErkhov/Weyaxi_-_SpeechlessV1-Nova-13B-gguf
Weyaxi_-_SpeechlessV1-Nova-13B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
219
15% of all-time downloads
All-time downloads
1.4K
Public
Repo size
130 GB
Likes
0
Public
Click a slice to open those files.
.gguf154 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
SpeechlessV1-Nova-13B - GGUF
| Name | Quant method | Size |
|---|---|---|
| SpeechlessV1-Nova-13B.Q2_K.gguf | Q2_K | 4.52GB |
| SpeechlessV1-Nova-13B.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| SpeechlessV1-Nova-13B.Q3_K.gguf | Q3_K | 5.9GB |
| SpeechlessV1-Nova-13B.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| SpeechlessV1-Nova-13B.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| SpeechlessV1-Nova-13B.IQ4_XS.gguf | IQ4_XS | 6.54GB |
| SpeechlessV1-Nova-13B.Q4_0.gguf | Q4_0 | 6.86GB |
| SpeechlessV1-Nova-13B.IQ4_NL.gguf | IQ4_NL | 6.9GB |
| SpeechlessV1-Nova-13B.Q4_K_S.gguf | Q4_K_S | 6.91GB |
| SpeechlessV1-Nova-13B.Q4_K.gguf | Q4_K | 7.33GB |
| SpeechlessV1-Nova-13B.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| SpeechlessV1-Nova-13B.Q4_1.gguf | Q4_1 | 7.61GB |
| SpeechlessV1-Nova-13B.Q5_0.gguf | Q5_0 | 8.36GB |
| SpeechlessV1-Nova-13B.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| SpeechlessV1-Nova-13B.Q5_K.gguf | Q5_K | 8.6GB |
| SpeechlessV1-Nova-13B.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| SpeechlessV1-Nova-13B.Q5_1.gguf | Q5_1 | 9.1GB |
| SpeechlessV1-Nova-13B.Q6_K.gguf | Q6_K | 9.95GB |
| SpeechlessV1-Nova-13B.Q8_0.gguf | Q8_0 | 12.88GB |
Original model description: https://huggingface.co/uukuguy/speechless-llama2-luban-orca-platypus-13b
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 49.41 |
| ARC (25-shot) | 61.77 |
| HellaSwag (10-shot) | 82.68 |
| MMLU (5-shot) | 57.75 |
| TruthfulQA (0-shot) | 51.44 |
| Winogrande (5-shot) | 77.43 |
| GSM8K (5-shot) | 5.76 |
| DROP (3-shot) | 9.05 |