Downloads · 30 days
129
9% of all-time downloads
RichardErkhov/augmxnt_-_shisa-gamma-7b-v1-gguf
augmxnt_-_shisa-gamma-7b-v1-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
129
9% of all-time downloads
All-time downloads
1.5K
Public
Repo size
72.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf85.7 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
shisa-gamma-7b-v1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| shisa-gamma-7b-v1.Q2_K.gguf | Q2_K | 2.53GB |
| shisa-gamma-7b-v1.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| shisa-gamma-7b-v1.Q3_K.gguf | Q3_K | 3.28GB |
| shisa-gamma-7b-v1.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| shisa-gamma-7b-v1.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| shisa-gamma-7b-v1.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| shisa-gamma-7b-v1.Q4_0.gguf | Q4_0 | 3.83GB |
| shisa-gamma-7b-v1.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| shisa-gamma-7b-v1.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| shisa-gamma-7b-v1.Q4_K.gguf | Q4_K | 4.07GB |
| shisa-gamma-7b-v1.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| shisa-gamma-7b-v1.Q4_1.gguf | Q4_1 | 4.24GB |
| shisa-gamma-7b-v1.Q5_0.gguf | Q5_0 | 4.65GB |
| shisa-gamma-7b-v1.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| shisa-gamma-7b-v1.Q5_K.gguf | Q5_K | 4.78GB |
| shisa-gamma-7b-v1.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| shisa-gamma-7b-v1.Q5_1.gguf | Q5_1 | 5.07GB |
| shisa-gamma-7b-v1.Q6_K.gguf | Q6_K | 5.53GB |
| shisa-gamma-7b-v1.Q8_0.gguf | Q8_0 | 7.17GB |
license: apache-2.0 datasets:
For more information see our main Shisa 7B model
We applied a version of our fine-tune data set onto Japanese Stable LM Base Gamma 7B and it performed pretty well, just sharing since it might be of interest.
Check out our JA MT-Bench results.

