Downloads · 30 days
1.6K
3% of all-time downloads
anthracite-org/magnum-v2.5-12b-kto-gguf
magnum-v2.5-12b-kto-gguf is a text generation model from anthracite-org. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Downloads · 30 days
1.6K
3% of all-time downloads
All-time downloads
53.9K
Public
Repo size
47.3 GB
Likes
42
Public
Click a slice to open those files.
.gguf47.3 GB · 100%
From the Hugging Face model README

v2.5 KTO is an experimental release; we are testing a hybrid reinforcement learning strategy of KTO + DPOP, using rejected data sampled from the original model as "rejected". For "chosen", we use data from the original finetuning dataset as "chosen". This was done on a limited portion of of primarily instruction following data; we plan to scale up a larger KTO dataset in the future for better generalization.
This is the 5th in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of anthracite-org/magnum-12b-v2.
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
This model has been a team effort, and the credits goes to all members of Anthracite.
...