README.md

metadata

language:
  - en
license: apache-2.0
library_name: transformers
datasets:
  - totally-not-an-llm/sharegpt-hyperfiltered-3k
pipeline_tag: text-generation
model-index:
  - name: Puma-3B
    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: 41.3
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
          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: 71.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
          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: 27.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
          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: 38.34
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
          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: 66.38
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
          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: 0.76
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
          name: Open LLM Leaderboard

This is OpenLLaMA 3B V2 finetuned on ShareGPT Hyperfiltered for 1 epochs.

Prompt template:

### HUMAN:
{prompt}

### RESPONSE:
<leave a newline for the model to answer>

GGML quants available here.
GPTQ quants available here.

Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please!

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	41.02
ARC (25-shot)	41.3
HellaSwag (10-shot)	71.85
MMLU (5-shot)	27.51
TruthfulQA (0-shot)	38.34
Winogrande (5-shot)	66.38
GSM8K (5-shot)	0.76

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	41.02
AI2 Reasoning Challenge (25-Shot)	41.30
HellaSwag (10-Shot)	71.85
MMLU (5-Shot)	27.51
TruthfulQA (0-shot)	38.34
Winogrande (5-shot)	66.38
GSM8k (5-shot)	0.76