This repo contains GGUF quants of the model. If you need the original weights, please find them here.

imatrix_data included

image/png

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.

Prompting

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
"""

Credits

This model has been a team effort, and the credits goes to all members of Anthracite.

Safety

...

Downloads last month
2,904
GGUF
Model size
12.2B params
Architecture
llama

3-bit

4-bit

5-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for anthracite-org/magnum-v2.5-12b-kto-gguf

Collection including anthracite-org/magnum-v2.5-12b-kto-gguf