Downloads · 30 days
93
5% of all-time downloads
mlabonne_-_UltraMerge-7B-gguf
RichardErkhov/mlabonne_-_UltraMerge-7B-gguf
mlabonne_-_UltraMerge-7B-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
1.8K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 14, 2024
- Updated
- Sep 14, 2024
- SHA
- 4e1753c8
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
UltraMerge-7B - GGUF
- Model creator: https://huggingface.co/mlabonne/
- Original model: https://huggingface.co/mlabonne/UltraMerge-7B/
| Name | Quant method | Size |
|---|---|---|
| UltraMerge-7B.Q2_K.gguf | Q2_K | 2.53GB |
| UltraMerge-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| UltraMerge-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| UltraMerge-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| UltraMerge-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| UltraMerge-7B.Q3_K.gguf | Q3_K | 3.28GB |
| UltraMerge-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| UltraMerge-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| UltraMerge-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| UltraMerge-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| UltraMerge-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| UltraMerge-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| UltraMerge-7B.Q4_K.gguf | Q4_K | 4.07GB |
| UltraMerge-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| UltraMerge-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| UltraMerge-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| UltraMerge-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| UltraMerge-7B.Q5_K.gguf | Q5_K | 4.78GB |
| UltraMerge-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| UltraMerge-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| UltraMerge-7B.Q6_K.gguf | Q6_K | 5.53GB |
| UltraMerge-7B.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
library_name: transformers license: cc-by-nc-4.0 tags:
- merge
- automerger
UltraMerge-7B
This model is an experimental DPO fine-tune of automerger/YamShadow-7B on the following datasets:
- mlabonne/truthy-dpo-v0.1
- mlabonne/distilabel-intel-orca-dpo-pairs
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
- mlabonne/ultrafeedback-binarized-preferences-cleaned
I have no idea about what's the best chat template. Probably Mistral-Instruct or ChatML.
- Created
- Sep 14, 2024
- Updated
- Sep 14, 2024