Downloads · 30 days
44
12% of all-time downloads
RichardErkhov/amazingvince_-_openhermes-7b-dpo-gguf
amazingvince_-_openhermes-7b-dpo-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
44
12% of all-time downloads
All-time downloads
381
Public
Repo size
82.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
openhermes-7b-dpo - GGUF
| Name | Quant method | Size |
|---|---|---|
| openhermes-7b-dpo.Q2_K.gguf | Q2_K | 2.53GB |
| openhermes-7b-dpo.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| openhermes-7b-dpo.IQ3_S.gguf | IQ3_S | 2.96GB |
| openhermes-7b-dpo.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| openhermes-7b-dpo.IQ3_M.gguf | IQ3_M | 3.06GB |
| openhermes-7b-dpo.Q3_K.gguf | Q3_K | 3.28GB |
| openhermes-7b-dpo.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| openhermes-7b-dpo.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| openhermes-7b-dpo.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| openhermes-7b-dpo.Q4_0.gguf | Q4_0 | 3.83GB |
| openhermes-7b-dpo.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| openhermes-7b-dpo.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| openhermes-7b-dpo.Q4_K.gguf | Q4_K | 4.07GB |
| openhermes-7b-dpo.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| openhermes-7b-dpo.Q4_1.gguf | Q4_1 | 4.24GB |
| openhermes-7b-dpo.Q5_0.gguf | Q5_0 | 4.65GB |
| openhermes-7b-dpo.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| openhermes-7b-dpo.Q5_K.gguf | Q5_K | 4.78GB |
| openhermes-7b-dpo.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| openhermes-7b-dpo.Q5_1.gguf | Q5_1 | 5.07GB |
| openhermes-7b-dpo.Q6_K.gguf | Q6_K | 5.53GB |
| openhermes-7b-dpo.Q8_0.gguf | Q8_0 | 7.17GB |
New experimental dpo tune. More details to come...
odel description OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
Here, we are finetuning openheremes using DPO with various data meant to improve its abilities.