Quantization made by Richard Erkhov.

jaskier-7b-dpo-v5.6 - GGUF

Model creator: https://huggingface.co/bardsai/
Original model: https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6/

Name	Quant method	Size
jaskier-7b-dpo-v5.6.Q2_K.gguf	Q2_K	2.53GB
jaskier-7b-dpo-v5.6.IQ3_XS.gguf	IQ3_XS	2.81GB
jaskier-7b-dpo-v5.6.IQ3_S.gguf	IQ3_S	2.96GB
jaskier-7b-dpo-v5.6.Q3_K_S.gguf	Q3_K_S	2.95GB
jaskier-7b-dpo-v5.6.IQ3_M.gguf	IQ3_M	3.06GB
jaskier-7b-dpo-v5.6.Q3_K.gguf	Q3_K	3.28GB
jaskier-7b-dpo-v5.6.Q3_K_M.gguf	Q3_K_M	3.28GB
jaskier-7b-dpo-v5.6.Q3_K_L.gguf	Q3_K_L	3.56GB
jaskier-7b-dpo-v5.6.IQ4_XS.gguf	IQ4_XS	3.67GB
jaskier-7b-dpo-v5.6.Q4_0.gguf	Q4_0	3.83GB
jaskier-7b-dpo-v5.6.IQ4_NL.gguf	IQ4_NL	3.87GB
jaskier-7b-dpo-v5.6.Q4_K_S.gguf	Q4_K_S	3.86GB
jaskier-7b-dpo-v5.6.Q4_K.gguf	Q4_K	4.07GB
jaskier-7b-dpo-v5.6.Q4_K_M.gguf	Q4_K_M	4.07GB
jaskier-7b-dpo-v5.6.Q4_1.gguf	Q4_1	4.24GB
jaskier-7b-dpo-v5.6.Q5_0.gguf	Q5_0	4.65GB
jaskier-7b-dpo-v5.6.Q5_K_S.gguf	Q5_K_S	4.65GB
jaskier-7b-dpo-v5.6.Q5_K.gguf	Q5_K	4.78GB
jaskier-7b-dpo-v5.6.Q5_K_M.gguf	Q5_K_M	4.78GB
jaskier-7b-dpo-v5.6.Q5_1.gguf	Q5_1	5.07GB
jaskier-7b-dpo-v5.6.Q6_K.gguf	Q6_K	5.53GB
jaskier-7b-dpo-v5.6.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers tags: - llm - 7b license: cc-by-4.0 language: - en datasets: - argilla/distilabel-math-preference-dpo

Jaskier-7b-dpo-v5.6

This is work-in-progress model, may not be ready for production use

Model based on paulml/OGNO-7B (downstream version of Mistral7B) finetuned using Direct Preference Optimization on argilla/distilabel-math-preference-dpo.

How to use

You can use this model directly with a Hugging Face pipeline:


from transformers import pipeline, Conversation
import torch

base_model_name = "bardsai/jaskier-7b-dpo-v5.6"
chatbot = pipeline("conversational", model=base_model_name, torch_dtype=torch.float16, device_map="auto")
conversation = Conversation("Is bard an ML engineer?")
conversation = chatbot(conversation)
print(conversation.messages[-1]["content"])

Output

"There is no direct personal connection between the concept of a "bard" and an "ML engineer." A bard is a mythical or literary figure, often a storyteller or musician, while an ML engineer refers to a Machine Learning engineer, a professional in the tech industry. They are unrelated entities, one fictional and the other a real-world occupation."

If you still find any issues with "INST" character chain appearing in generated output, try our newest model: https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1 . Re-tasking the prompt can also help.

Changelog

2024-02-16: Initial release

About bards.ai

At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: bards.ai

Let us know if you use our model :). Also, if you need any help, feel free to contact us at info@bards.ai