This is the first 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 Qwen-2 72B Instruct.

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.

We'd also like to thank Kearm for sponsoring the compute needed to train this model.

Training

The training was done with 55 million tokens of high-quality RP data, over 1.5 epochs. We used 8x AMD Instinct™ MI300X Accelerators for the full-parameter fine-tuning of the model.

Built with Axolotl

Safety

...

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 42.17
IFEval (0-Shot) 76.06
BBH (3-Shot) 57.65
MATH Lvl 5 (4-Shot) 35.27
GPQA (0-shot) 18.79
MuSR (0-shot) 15.62
MMLU-PRO (5-shot) 49.64

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 42.21
IFEval (0-Shot) 76.06
BBH (3-Shot) 57.65
MATH Lvl 5 (4-Shot) 35.27
GPQA (0-shot) 18.79
MuSR (0-shot) 15.62
MMLU-PRO (5-shot) 49.85
Downloads last month
5,589
Safetensors
Model size
72.7B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for anthracite-org/magnum-v1-72b

Base model

Qwen/Qwen2-72B
Finetuned
(6)
this model
Merges
4 models
Quantizations
4 models

Collection including anthracite-org/magnum-v1-72b

Evaluation results