Downloads · 30 days
111
6% of all-time downloads
RichardErkhov/vistagi_-_Mixtral-8x7b-v0.1-sft-gguf
vistagi_-_Mixtral-8x7b-v0.1-sft-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
111
6% of all-time downloads
All-time downloads
2K
Public
Repo size
510 GB
Likes
0
Public
Click a slice to open those files.
.gguf594 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Mixtral-8x7b-v0.1-sft - GGUF
| Name | Quant method | Size |
|---|---|---|
| Mixtral-8x7b-v0.1-sft.Q2_K.gguf | Q2_K | 16.12GB |
| Mixtral-8x7b-v0.1-sft.IQ3_XS.gguf | IQ3_XS | 18.02GB |
| Mixtral-8x7b-v0.1-sft.IQ3_S.gguf | IQ3_S | 19.03GB |
| Mixtral-8x7b-v0.1-sft.Q3_K_S.gguf | Q3_K_S | 19.03GB |
| Mixtral-8x7b-v0.1-sft.IQ3_M.gguf | IQ3_M | 19.96GB |
| Mixtral-8x7b-v0.1-sft.Q3_K.gguf | Q3_K | 21.0GB |
| Mixtral-8x7b-v0.1-sft.Q3_K_M.gguf | Q3_K_M | 21.0GB |
| Mixtral-8x7b-v0.1-sft.Q3_K_L.gguf | Q3_K_L | 4.27GB |
| Mixtral-8x7b-v0.1-sft.IQ4_XS.gguf | IQ4_XS | 23.63GB |
| Mixtral-8x7b-v0.1-sft.Q4_0.gguf | Q4_0 | 24.63GB |
| Mixtral-8x7b-v0.1-sft.IQ4_NL.gguf | IQ4_NL | 24.91GB |
| Mixtral-8x7b-v0.1-sft.Q4_K_S.gguf | Q4_K_S | 24.91GB |
| Mixtral-8x7b-v0.1-sft.Q4_K.gguf | Q4_K | 26.49GB |
| Mixtral-8x7b-v0.1-sft.Q4_K_M.gguf | Q4_K_M | 26.49GB |
| Mixtral-8x7b-v0.1-sft.Q4_1.gguf | Q4_1 | 27.32GB |
| Mixtral-8x7b-v0.1-sft.Q5_0.gguf | Q5_0 | 30.02GB |
| Mixtral-8x7b-v0.1-sft.Q5_K_S.gguf | Q5_K_S | 30.02GB |
| Mixtral-8x7b-v0.1-sft.Q5_K.gguf | Q5_K | 30.95GB |
| Mixtral-8x7b-v0.1-sft.Q5_K_M.gguf | Q5_K_M | 30.95GB |
| Mixtral-8x7b-v0.1-sft.Q5_1.gguf | Q5_1 | 32.71GB |
| Mixtral-8x7b-v0.1-sft.Q6_K.gguf | Q6_K | 35.74GB |
| Mixtral-8x7b-v0.1-sft.Q8_0.gguf | Q8_0 | 46.22GB |
license: apache-2.0 datasets:
This model vistagi/Mixtral-8x7b-v0.1-sft is trained with Ultrachat-200K dataset through supervised finetuning using Mixtral-8x7b-v0.1 as the baseline model. The training is done with bfloat16 precision using LoRA.
Used Librarys