RichardErkhov/lemon-mint_-_gemma-7b-openhermes-v0.80-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-7b-openhermes-v0.80 - GGUF

• Model creator: https://huggingface.co/lemon-mint/
• Original model: https://huggingface.co/lemon-mint/gemma-7b-openhermes-v0.80/

Name	Quant method	Size
gemma-7b-openhermes-v0.80.Q2_K.gguf	Q2_K	3.24GB
gemma-7b-openhermes-v0.80.IQ3_XS.gguf	IQ3_XS	3.54GB
gemma-7b-openhermes-v0.80.IQ3_S.gguf	IQ3_S	3.71GB
gemma-7b-openhermes-v0.80.Q3_K_S.gguf	Q3_K_S	3.71GB
gemma-7b-openhermes-v0.80.IQ3_M.gguf	IQ3_M	3.82GB
gemma-7b-openhermes-v0.80.Q3_K.gguf	Q3_K	4.07GB
gemma-7b-openhermes-v0.80.Q3_K_M.gguf	Q3_K_M	4.07GB
gemma-7b-openhermes-v0.80.Q3_K_L.gguf	Q3_K_L	4.39GB
gemma-7b-openhermes-v0.80.IQ4_XS.gguf	IQ4_XS	4.48GB
gemma-7b-openhermes-v0.80.Q4_0.gguf	Q4_0	4.67GB
gemma-7b-openhermes-v0.80.IQ4_NL.gguf	IQ4_NL	4.69GB
gemma-7b-openhermes-v0.80.Q4_K_S.gguf	Q4_K_S	4.7GB
gemma-7b-openhermes-v0.80.Q4_K.gguf	Q4_K	4.96GB
gemma-7b-openhermes-v0.80.Q4_K_M.gguf	Q4_K_M	4.96GB
gemma-7b-openhermes-v0.80.Q4_1.gguf	Q4_1	5.12GB
gemma-7b-openhermes-v0.80.Q5_0.gguf	Q5_0	5.57GB
gemma-7b-openhermes-v0.80.Q5_K_S.gguf	Q5_K_S	5.57GB
gemma-7b-openhermes-v0.80.Q5_K.gguf	Q5_K	5.72GB
gemma-7b-openhermes-v0.80.Q5_K_M.gguf	Q5_K_M	5.72GB
gemma-7b-openhermes-v0.80.Q5_1.gguf	Q5_1	6.02GB
gemma-7b-openhermes-v0.80.Q6_K.gguf	Q6_K	6.53GB
gemma-7b-openhermes-v0.80.Q8_0.gguf	Q8_0	8.45GB

Original model description:

library_name: transformers language: - en license: gemma tags: - gemma - pytorch - instruct - finetune base_model: google/gemma-1.1-7b-it pipeline_tag: text-generation datasets: - teknium/OpenHermes-2.5

Gemma 7B OpenHermes v0.80

• Eval Loss: 0.4544
• Train Loss: 0.3129
• lr: 5e-5
• optimizer: adamw
• lr_scheduler_type: cosine

Model Details

This is an instruction-following model finetuned from the Gemma 1.1 7B model. It was finetuned on the OpenHermes-2.5 dataset to improve its ability to engage in open-ended conversation and respond helpfully to user instructions and queries. The model can engage in dialogue, answer questions, and assist with a variety of tasks.

Model Description

• Developed by: lemon-mint
• Model type: Gemma
• Language(s) (NLP): English
• License: gemma-terms-of-use
• Finetuned from model: google/gemma-1.1-7b-it

Limitations and Ethical Considerations

As Gemma 7B OpenHermes has been trained on extensive web data, biases present in the training data may be reflected in the model. Additionally, there is a possibility that it may generate sentences containing errors or incorrect information. Therefore, rather than blindly trusting the model's output, it is necessary to refer to it with caution.