metadata

language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ru
  - zh
  - ja
license: other
tags:
  - chat
base_model: Qwen/Qwen2-72B-Instruct
datasets:
  - Doctor-Shotgun/C2-Stheno
  - anthracite-org/kalo-opus-instruct-22k-no-refusal
  - anthracite-org/nopm_claude_writing_fixed
license_name: tongyi-qianwen
license_link: https://huggingface.co/anthracite-org/magnum-v2-72b/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
  - name: magnum-v2-72b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 75.6
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 57.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 31.65
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 18.12
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 14.18
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 49.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v2-72b
          name: Open LLM Leaderboard

This is the seventh (Lucky!) 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.

Training

The training was done for 2 epochs. We used 8x AMD Instinct™ MI300X Accelerators for the full-parameter fine-tuning of the model.

We also trained with a weight decay of 0.01 to help further stabilize the loss trajectory and mitigate catastrophic forgetting, and utilize a peak learning rate of 4e-6 to prevent the 2nd epoch loss from dropping too significantly (as it is a strong indicator of overfitting).

Sample Packing was done for 16k tokens rather than the 8k tokens used in our previous runs.

Safety

...

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	41.15
IFEval (0-Shot)	75.60
BBH (3-Shot)	57.85
MATH Lvl 5 (4-Shot)	31.65
GPQA (0-shot)	18.12
MuSR (0-shot)	14.18
MMLU-PRO (5-shot)	49.51