Quantization made by Richard Erkhov.

jaskier-7b-dpo-v6.1 - GGUF

Model creator: https://huggingface.co/bardsai/
Original model: https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1/

Name	Quant method	Size
jaskier-7b-dpo-v6.1.Q2_K.gguf	Q2_K	2.53GB
jaskier-7b-dpo-v6.1.IQ3_XS.gguf	IQ3_XS	2.81GB
jaskier-7b-dpo-v6.1.IQ3_S.gguf	IQ3_S	2.96GB
jaskier-7b-dpo-v6.1.Q3_K_S.gguf	Q3_K_S	2.95GB
jaskier-7b-dpo-v6.1.IQ3_M.gguf	IQ3_M	3.06GB
jaskier-7b-dpo-v6.1.Q3_K.gguf	Q3_K	3.28GB
jaskier-7b-dpo-v6.1.Q3_K_M.gguf	Q3_K_M	3.28GB
jaskier-7b-dpo-v6.1.Q3_K_L.gguf	Q3_K_L	3.56GB
jaskier-7b-dpo-v6.1.IQ4_XS.gguf	IQ4_XS	3.67GB
jaskier-7b-dpo-v6.1.Q4_0.gguf	Q4_0	3.83GB
jaskier-7b-dpo-v6.1.IQ4_NL.gguf	IQ4_NL	3.87GB
jaskier-7b-dpo-v6.1.Q4_K_S.gguf	Q4_K_S	3.86GB
jaskier-7b-dpo-v6.1.Q4_K.gguf	Q4_K	4.07GB
jaskier-7b-dpo-v6.1.Q4_K_M.gguf	Q4_K_M	4.07GB
jaskier-7b-dpo-v6.1.Q4_1.gguf	Q4_1	4.24GB
jaskier-7b-dpo-v6.1.Q5_0.gguf	Q5_0	4.65GB
jaskier-7b-dpo-v6.1.Q5_K_S.gguf	Q5_K_S	4.65GB
jaskier-7b-dpo-v6.1.Q5_K.gguf	Q5_K	4.78GB
jaskier-7b-dpo-v6.1.Q5_K_M.gguf	Q5_K_M	4.78GB
jaskier-7b-dpo-v6.1.Q5_1.gguf	Q5_1	5.07GB
jaskier-7b-dpo-v6.1.Q6_K.gguf	Q6_K	5.53GB
jaskier-7b-dpo-v6.1.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers tags: - llm - 7b license: cc-by-4.0 datasets: - jondurbin/truthy-dpo-v0.1 language: - en

Jaskier-7b-dpo-v5.6

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

Model based on bardsai/jaskier-7b-dpo-v5.6 (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-v6.1"
chatbot = pipeline("conversational", model=base_model_name, torch_dtype=torch.float16, device_map="auto")
conversation = Conversation("Can Poland into space?")
conversation = chatbot(conversation)
print(conversation.messages[-1]["content"])

Output

"Poland, as a nation, doesn't physically travel to space. However, Poland has contributed to the field of space exploration through its scientists, engineers, and collaborations with international space agencies. The Polish Space Agency, established in 2016, aims to promote and coordinate the country's space activities."

Changelog

2024-02-20: 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