CorticalStack_-_mistral-7b-openhermes-2.5-sft-gguf

RichardErkhov/CorticalStack_-_mistral-7b-openhermes-2.5-sft-gguf

CorticalStack_-_mistral-7b-openhermes-2.5-sft-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

315

15% of all-time downloads

All-time downloads

2.2K

Public

Repo size

82.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf95.2 GB · 100%

At a glance

Access: Public
Created: Sep 6, 2024
Updated: Sep 6, 2024
SHA: 819d749b

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-7b-openhermes-2.5-sft - GGUF

Model creator: https://huggingface.co/CorticalStack/
Original model: https://huggingface.co/CorticalStack/mistral-7b-openhermes-2.5-sft/

Name	Quant method	Size
mistral-7b-openhermes-2.5-sft.Q2_K.gguf	Q2_K	2.53GB
mistral-7b-openhermes-2.5-sft.IQ3_XS.gguf	IQ3_XS	2.81GB
mistral-7b-openhermes-2.5-sft.IQ3_S.gguf	IQ3_S	2.96GB
mistral-7b-openhermes-2.5-sft.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral-7b-openhermes-2.5-sft.IQ3_M.gguf	IQ3_M	3.06GB
mistral-7b-openhermes-2.5-sft.Q3_K.gguf	Q3_K	3.28GB
mistral-7b-openhermes-2.5-sft.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral-7b-openhermes-2.5-sft.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral-7b-openhermes-2.5-sft.IQ4_XS.gguf	IQ4_XS	3.67GB
mistral-7b-openhermes-2.5-sft.Q4_0.gguf	Q4_0	3.83GB
mistral-7b-openhermes-2.5-sft.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral-7b-openhermes-2.5-sft.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral-7b-openhermes-2.5-sft.Q4_K.gguf	Q4_K	4.07GB
mistral-7b-openhermes-2.5-sft.Q4_K_M.gguf	Q4_K_M	4.07GB
mistral-7b-openhermes-2.5-sft.Q4_1.gguf	Q4_1	4.24GB
mistral-7b-openhermes-2.5-sft.Q5_0.gguf	Q5_0	4.65GB
mistral-7b-openhermes-2.5-sft.Q5_K_S.gguf	Q5_K_S	4.65GB
mistral-7b-openhermes-2.5-sft.Q5_K.gguf	Q5_K	4.78GB
mistral-7b-openhermes-2.5-sft.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral-7b-openhermes-2.5-sft.Q5_1.gguf	Q5_1	5.07GB
mistral-7b-openhermes-2.5-sft.Q6_K.gguf	Q6_K	5.53GB
mistral-7b-openhermes-2.5-sft.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0

mistral-7b-openhermes-2.5-sft

mistral-7b-openhermes-2.5-sft is an SFT fine-tuned version of unsloth/mistral-7b-bnb-4bit using the teknium/OpenHermes-2.5 dataset.

Fine-tuning configuration

LoRA

r: 256
LoRA alpha: 128
LoRA dropout: 0.0

Training arguments

Epochs: 1
Batch size: 4
Gradient accumulation steps: 6
Optimizer: adamw_torch_fused
Max steps: 100
Learning rate: 0.0002
Weight decay: 0.1
Learning rate scheduler type: linear
Max seq length: 2048
4-bit bnb: True

Trained with Unsloth and Huggingface's TRL library.

Created: Sep 6, 2024
Updated: Sep 6, 2024