Downloads · 30 days
12
4% of all-time downloads
Undi95_-_MG-FinalMix-72B-gguf
RichardErkhov/Undi95_-_MG-FinalMix-72B-gguf
Undi95_-_MG-FinalMix-72B-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.
All-time downloads
316
Public
Repo size
689 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf829 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 5, 2024
- Updated
- Nov 6, 2024
- SHA
- cfcbca63
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
MG-FinalMix-72B - GGUF
- Model creator: https://huggingface.co/Undi95/
- Original model: https://huggingface.co/Undi95/MG-FinalMix-72B/
| Name | Quant method | Size |
|---|---|---|
| MG-FinalMix-72B.Q2_K.gguf | Q2_K | 27.76GB |
| MG-FinalMix-72B.Q3_K_S.gguf | Q3_K_S | 32.12GB |
| MG-FinalMix-72B.Q3_K.gguf | Q3_K | 35.11GB |
| MG-FinalMix-72B.Q3_K_M.gguf | Q3_K_M | 35.11GB |
| MG-FinalMix-72B.Q3_K_L.gguf | Q3_K_L | 36.79GB |
| MG-FinalMix-72B.IQ4_XS.gguf | IQ4_XS | 37.4GB |
| MG-FinalMix-72B.Q4_0.gguf | Q4_0 | 38.4GB |
| MG-FinalMix-72B.IQ4_NL.gguf | IQ4_NL | 38.9GB |
| MG-FinalMix-72B.Q4_K_S.gguf | Q4_K_S | 40.88GB |
| MG-FinalMix-72B.Q4_K.gguf | Q4_K | 44.16GB |
| MG-FinalMix-72B.Q4_K_M.gguf | Q4_K_M | 44.16GB |
| MG-FinalMix-72B.Q4_1.gguf | Q4_1 | 42.56GB |
| MG-FinalMix-72B.Q5_0.gguf | Q5_0 | 46.72GB |
| MG-FinalMix-72B.Q5_K_S.gguf | Q5_K_S | 47.85GB |
| MG-FinalMix-72B.Q5_K.gguf | Q5_K | 50.71GB |
| MG-FinalMix-72B.Q5_K_M.gguf | Q5_K_M | 50.71GB |
| MG-FinalMix-72B.Q5_1.gguf | Q5_1 | 50.88GB |
| MG-FinalMix-72B.Q6_K.gguf | Q6_K | 59.93GB |
| MG-FinalMix-72B.Q8_0.gguf | Q8_0 | 71.96GB |
Original model description:
base_model:
- Qwen/Qwen2-72B-Instruct
- alpindale/magnum-72b-v1 library_name: transformers tags:
- mergekit
- merge
- OG_finetune_merge license: other language:
- en
WIP of retouched alpindale/magnum-72b-v1 but I will not use "Magnum" in the name. Call it FinalMix!
Found some issues, trying to fix them for my own usage and adding more RP data with merging.
You can do your own quantized files with the imatrix.dat file done with "wiki.train.raw".
Credits to Alpin and the gang for magnum-72b-v1, and Ikari for his datasets.
Prompt template ChatML
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
{output}<|im_end|>
- Created
- Nov 5, 2024
- Updated
- Nov 6, 2024