README.md

metadata

language:
  - en
license: cc-by-2.0
tags:
  - finance
  - legal
  - biology
  - art
model-index:
  - name: SatoshiNv5
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 60.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chrischain/SatoshiNv5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 82.94
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chrischain/SatoshiNv5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 63.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chrischain/SatoshiNv5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 41.8
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chrischain/SatoshiNv5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 78.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chrischain/SatoshiNv5
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 34.72
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chrischain/SatoshiNv5
          name: Open LLM Leaderboard

Behold, one of the first fine-tunes of Mistral's 7B 0.2 Base model. SatoshiN is trained on 4 epochs 2e-4 learning rate (cosine) of a diverse custom data-set, combined with a polishing round of that same data-set at a 1e-4 linear learning rate. It's a nice assistant that isn't afraid to ask questions, and gather additional information before providing a response to user prompts.

SatoshiN | Base-Model

Wikitext Perplexity: 6.27 | 5.4

**Similar to SOTA, this model runs a bit hot, try using lower temperatures below .5 if experiencing any nonsense)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	60.34
AI2 Reasoning Challenge (25-Shot)	60.49
HellaSwag (10-Shot)	82.94
MMLU (5-Shot)	63.42
TruthfulQA (0-shot)	41.80
Winogrande (5-shot)	78.69
GSM8k (5-shot)	34.72