Downloads · 30 days
6
1% of all-time downloads
RichardErkhov/llmixer_-_BigWeave-v6-90b-gguf
llmixer_-_BigWeave-v6-90b-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
6
1% of all-time downloads
All-time downloads
781
Public
Repo size
989 GB
Likes
0
Public
Click a slice to open those files.
.gguf1.1 TB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
BigWeave-v6-90b - GGUF
| Name | Quant method | Size |
|---|---|---|
| BigWeave-v6-90b.Q2_K.gguf | Q2_K | 30.06GB |
| BigWeave-v6-90b.IQ3_XS.gguf | IQ3_XS | 33.43GB |
| BigWeave-v6-90b.IQ3_S.gguf | IQ3_S | 35.34GB |
| BigWeave-v6-90b.Q3_K_S.gguf | Q3_K_S | 35.24GB |
| BigWeave-v6-90b.IQ3_M.gguf | IQ3_M | 36.54GB |
| BigWeave-v6-90b.Q3_K.gguf | Q3_K | 39.32GB |
| BigWeave-v6-90b.Q3_K_M.gguf | Q3_K_M | 39.32GB |
| BigWeave-v6-90b.Q3_K_L.gguf | Q3_K_L | 42.84GB |
| BigWeave-v6-90b.IQ4_XS.gguf | IQ4_XS | 44.05GB |
| BigWeave-v6-90b.Q4_0.gguf | Q4_0 | 46.07GB |
| BigWeave-v6-90b.IQ4_NL.gguf | IQ4_NL | 46.49GB |
| BigWeave-v6-90b.Q4_K_S.gguf | Q4_K_S | 46.4GB |
| BigWeave-v6-90b.Q4_K.gguf | Q4_K | 48.99GB |
| BigWeave-v6-90b.Q4_K_M.gguf | Q4_K_M | 48.99GB |
| BigWeave-v6-90b.Q4_1.gguf | Q4_1 | 51.16GB |
| BigWeave-v6-90b.Q5_0.gguf | Q5_0 | 56.26GB |
| BigWeave-v6-90b.Q5_K_S.gguf | Q5_K_S | 56.26GB |
| BigWeave-v6-90b.Q5_K.gguf | Q5_K | 57.76GB |
| BigWeave-v6-90b.Q5_K_M.gguf | Q5_K_M | 57.76GB |
| BigWeave-v6-90b.Q5_1.gguf | Q5_1 | 61.35GB |
| BigWeave-v6-90b.Q6_K.gguf | Q6_K | 67.08GB |
| BigWeave-v6-90b.Q8_0.gguf | Q8_0 | 86.89GB |
language:
A Goliath-120b style frankenmerge of Xwin-LM-70b-v0.1 and Euryale-1.3-70b. The goal is to find other merge combinations that work well.
The version number is for me to keep track of the merges, only results that seem to work reasonably well are kept/published.
Vicuna and Alpaca.
The models used in the merge are Xwin-LM-70b-v0.1 and Euryale-1.3-70b.
The layer mix:
- range 0, 12
Xwin
- range 9, 14
Euryale
- range 12, 62
Xwin
- range 54, 71
Euryale
- range 62, 80
Xwin
@Xwin-LM For creating Xwin
@Sao10K For creating Euryale
@alpindale For creating the original Goliath
@chargoddard For developing mergekit.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.47 |
| AI2 Reasoning Challenge (25-Shot) | 65.36 |
| HellaSwag (10-Shot) | 87.21 |
| MMLU (5-Shot) | 68.04 |
| TruthfulQA (0-shot) | 57.96 |
| Winogrande (5-shot) | 81.69 |
| GSM8k (5-shot) | 44.58 |