README.md

metadata

language:
  - en
license: cc-by-nc-4.0
model-index:
  - name: MN-12B-Lyra-v3
    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: 44.86
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sao10K/MN-12B-Lyra-v3
          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: 25.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sao10K/MN-12B-Lyra-v3
          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: 7.18
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sao10K/MN-12B-Lyra-v3
          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: 3.69
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sao10K/MN-12B-Lyra-v3
          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: 9.04
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sao10K/MN-12B-Lyra-v3
          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: 24.99
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Sao10K/MN-12B-Lyra-v3
          name: Open LLM Leaderboard

Ungated. Thanks for the patience!

---

Mistral-NeMo-12B-Lyra-v3, built on top of Lyra-v2a2, which itself was built upon Lyra-v2a1.

Model Versioning

Lyra-v1 [Merge of Custom Roleplay & Instruct Trains, on Different Formats]
  |
  | [Additional SFT on 10% of Previous Data, Mixed]
  v
Lyra-v2a1 
  |
  | [Low Rank SFT Step + Tokenizer Diddling]
  v
Lyra-v2a2
  |
  | [RL Step Performed on Multiturn Sets, Magpie-style Responses by Lyra-v2a2 for Rejected Data]
  v
Lyra-v3

This uses a custom ChatML-style prompting Format!

-> What can go wrong?

[INST]system
This is the system prompt.[/INST]
[INST]user
Instructions placed here.[/INST]
[INST]assistant
The model's response will be here.[/INST]

Why this? I had used the wrong configs by accident. The format was meant for an 8B pruned NeMo train, instead it went to this. Oops.

Recommended Samplers:

Temperature: 0.7 - 1.2
min_p: 0.1 - 0.2 # Crucial for NeMo

Recommended Stopping Strings:

<|im_end|>
</s>

Blame messed up Training Configs, oops?

Training Metrics:

- Trained on 4xH100 SXM for 6 Hours.
- Trained for 2 Epochs.
- Effective Global Batch Size: 128.
- Dataset Used: A custom, cleaned mix of Stheno-v3.4's Dataset, focused mainly on multiturn.

---

Extras

Image Source: AI-Generated with FLUX.1 Dev.

have a nice day.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.27
IFEval (0-Shot)	44.86
BBH (3-Shot)	25.87
MATH Lvl 5 (4-Shot)	7.18
GPQA (0-shot)	3.69
MuSR (0-shot)	9.04
MMLU-PRO (5-shot)	24.99