👁 image/png

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus.

experimental because trained on top of instruct; but turned out amazing; hence code named magnum-alter, the original model that kickstarted the v4 family

This model is fine-tuned on top of Qwen2.5-72B-Instruct.

Prompting

A typical input would look like this:

<|im_start|>system
system prompt<|im_end|>
<|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

SillyTavern templates

Below are Instruct and Context templates for use within SillyTavern.

Axolotl config

Credits

We'd like to thank DoctorShotgun for sponsoring the compute for this train. We would also like to thank all members of Anthracite who made this finetune possible.

Datasets

• anthracite-org/c2_logs_32k_llama3_qwen2_v1.2
• anthracite-org/kalo-opus-instruct-22k-no-refusal
• lodrick-the-lafted/kalo-opus-instruct-3k-filtered
• anthracite-org/nopm_claude_writing_fixed
• anthracite-org/kalo_opus_misc_240827
• anthracite-org/kalo_misc_part2

Training

We used 8x mi300x GPUs graciously provided by DoctorShotgun for the full-parameter fine-tuning of the model.

👁 Built with Axolotl

Safety

...

18 items • Updated Oct 20, 2024 • 34