RichardErkhov/unsloth_-_Hermes-2-Pro-Mistral-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Hermes-2-Pro-Mistral-7B - GGUF

• Model creator: https://huggingface.co/unsloth/
• Original model: https://huggingface.co/unsloth/Hermes-2-Pro-Mistral-7B/

Name	Quant method	Size
Hermes-2-Pro-Mistral-7B.Q2_K.gguf	Q2_K	2.53GB
Hermes-2-Pro-Mistral-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Hermes-2-Pro-Mistral-7B.IQ3_S.gguf	IQ3_S	2.96GB
Hermes-2-Pro-Mistral-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Hermes-2-Pro-Mistral-7B.IQ3_M.gguf	IQ3_M	3.06GB
Hermes-2-Pro-Mistral-7B.Q3_K.gguf	Q3_K	3.28GB
Hermes-2-Pro-Mistral-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Hermes-2-Pro-Mistral-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Hermes-2-Pro-Mistral-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Hermes-2-Pro-Mistral-7B.Q4_0.gguf	Q4_0	3.83GB
Hermes-2-Pro-Mistral-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Hermes-2-Pro-Mistral-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Hermes-2-Pro-Mistral-7B.Q4_K.gguf	Q4_K	4.07GB
Hermes-2-Pro-Mistral-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Hermes-2-Pro-Mistral-7B.Q4_1.gguf	Q4_1	4.24GB
Hermes-2-Pro-Mistral-7B.Q5_0.gguf	Q5_0	4.65GB
Hermes-2-Pro-Mistral-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Hermes-2-Pro-Mistral-7B.Q5_K.gguf	Q5_K	4.78GB
Hermes-2-Pro-Mistral-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Hermes-2-Pro-Mistral-7B.Q5_1.gguf	Q5_1	5.07GB
Hermes-2-Pro-Mistral-7B.Q6_K.gguf	Q6_K	5.53GB
Hermes-2-Pro-Mistral-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

language:

• en license: apache-2.0 library_name: transformers tags:
• unsloth
• transformers
• yi
• yi-34b

---

Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Gemma 7b	▶️ Start on Colab	2.4x faster	58% less
Mistral 7b	▶️ Start on Colab	2.2x faster	62% less
Llama-2 7b	▶️ Start on Colab	2.2x faster	43% less
TinyLlama	▶️ Start on Colab	3.9x faster	74% less
CodeLlama 34b A100	▶️ Start on Colab	1.9x faster	27% less
Mistral 7b 1xT4	▶️ Start on Kaggle	5x faster*	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

• This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
• This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
• * Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.