Quantization made by Richard Erkhov.

Hippolyta-7B-bf16 - GGUF

Model creator: https://huggingface.co/Kquant03/
Original model: https://huggingface.co/Kquant03/Hippolyta-7B-bf16/

Name	Quant method	Size
Hippolyta-7B-bf16.Q2_K.gguf	Q2_K	2.53GB
Hippolyta-7B-bf16.IQ3_XS.gguf	IQ3_XS	2.81GB
Hippolyta-7B-bf16.IQ3_S.gguf	IQ3_S	2.96GB
Hippolyta-7B-bf16.Q3_K_S.gguf	Q3_K_S	2.95GB
Hippolyta-7B-bf16.IQ3_M.gguf	IQ3_M	3.06GB
Hippolyta-7B-bf16.Q3_K.gguf	Q3_K	3.28GB
Hippolyta-7B-bf16.Q3_K_M.gguf	Q3_K_M	3.28GB
Hippolyta-7B-bf16.Q3_K_L.gguf	Q3_K_L	3.56GB
Hippolyta-7B-bf16.IQ4_XS.gguf	IQ4_XS	3.67GB
Hippolyta-7B-bf16.Q4_0.gguf	Q4_0	3.83GB
Hippolyta-7B-bf16.IQ4_NL.gguf	IQ4_NL	3.87GB
Hippolyta-7B-bf16.Q4_K_S.gguf	Q4_K_S	3.86GB
Hippolyta-7B-bf16.Q4_K.gguf	Q4_K	4.07GB
Hippolyta-7B-bf16.Q4_K_M.gguf	Q4_K_M	4.07GB
Hippolyta-7B-bf16.Q4_1.gguf	Q4_1	4.24GB
Hippolyta-7B-bf16.Q5_0.gguf	Q5_0	4.65GB
Hippolyta-7B-bf16.Q5_K_S.gguf	Q5_K_S	4.65GB
Hippolyta-7B-bf16.Q5_K.gguf	Q5_K	4.78GB
Hippolyta-7B-bf16.Q5_K_M.gguf	Q5_K_M	4.78GB
Hippolyta-7B-bf16.Q5_1.gguf	Q5_1	5.07GB
Hippolyta-7B-bf16.Q6_K.gguf	Q6_K	5.53GB
Hippolyta-7B-bf16.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 datasets: - Open-Orca/OpenOrca - teknium/openhermes - cognitivecomputations/dolphin - jondurbin/airoboros-3.1 - unalignment/toxic-dpo-v0.1 - unalignment/spicy-3.1 language: - en

The flower of Ares.

GGUF files here

Fine-tuned on mistralai/Mistral-7B-v0.1...my team and I reformatted many different datasets and included a small amount of private stuff to see how much we could improve mistral.

I spoke to it personally for about an hour, and I believe we need to work on our format for the private dataset a bit more, but other than that, it turned out great. I will be uploading it to open llm evaluations, today.

Uses Mistral prompt template with chat-instruct.