freewheelin_-_free-llama3-dpo-v0.2-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
freewheelin_-_free-llama3-dpo-v0.2-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

free-llama3-dpo-v0.2 - GGUF

Model creator: https://huggingface.co/freewheelin/
Original model: https://huggingface.co/freewheelin/free-llama3-dpo-v0.2/

Name	Quant method	Size
free-llama3-dpo-v0.2.Q2_K.gguf	Q2_K	2.96GB
free-llama3-dpo-v0.2.IQ3_XS.gguf	IQ3_XS	3.28GB
free-llama3-dpo-v0.2.IQ3_S.gguf	IQ3_S	3.43GB
free-llama3-dpo-v0.2.Q3_K_S.gguf	Q3_K_S	3.41GB
free-llama3-dpo-v0.2.IQ3_M.gguf	IQ3_M	3.52GB
free-llama3-dpo-v0.2.Q3_K.gguf	Q3_K	3.74GB
free-llama3-dpo-v0.2.Q3_K_M.gguf	Q3_K_M	3.74GB
free-llama3-dpo-v0.2.Q3_K_L.gguf	Q3_K_L	4.03GB
free-llama3-dpo-v0.2.IQ4_XS.gguf	IQ4_XS	4.18GB
free-llama3-dpo-v0.2.Q4_0.gguf	Q4_0	4.34GB
free-llama3-dpo-v0.2.IQ4_NL.gguf	IQ4_NL	4.38GB
free-llama3-dpo-v0.2.Q4_K_S.gguf	Q4_K_S	4.37GB
free-llama3-dpo-v0.2.Q4_K.gguf	Q4_K	4.58GB
free-llama3-dpo-v0.2.Q4_K_M.gguf	Q4_K_M	4.58GB
free-llama3-dpo-v0.2.Q4_1.gguf	Q4_1	4.78GB
free-llama3-dpo-v0.2.Q5_0.gguf	Q5_0	5.21GB
free-llama3-dpo-v0.2.Q5_K_S.gguf	Q5_K_S	5.21GB
free-llama3-dpo-v0.2.Q5_K.gguf	Q5_K	5.34GB
free-llama3-dpo-v0.2.Q5_K_M.gguf	Q5_K_M	5.34GB
free-llama3-dpo-v0.2.Q5_1.gguf	Q5_1	5.65GB
free-llama3-dpo-v0.2.Q6_K.gguf	Q6_K	6.14GB
free-llama3-dpo-v0.2.Q8_0.gguf	Q8_0	7.95GB

Original model description:

language:

ko
en license: mit

Model Card for free-llama-dpo-v0.2

Developed by : Freewheelin AI Technical Team

Hardware and Software

Training Factors: We fine-tuned this model using the HuggingFace TRL Trainer

Method

This model was trained using the learning method introduced in the SOLAR paper.