README.md

metadata

license: other
library_name: transformers
tags:
  - code
pipeline_tag: text-generation
license_name: deepseek-license
license_link: LICENSE
model-index:
  - name: speechless-nl2sql-ds-6.7b
    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: 36.35
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-nl2sql-ds-6.7b
          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: 52.83
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-nl2sql-ds-6.7b
          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: 36.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-nl2sql-ds-6.7b
          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: 40.55
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-nl2sql-ds-6.7b
          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: 55.96
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-nl2sql-ds-6.7b
          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: 15.09
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-nl2sql-ds-6.7b
          name: Open LLM Leaderboard

speechless-nl2sql-ds-6.7b

4,5,8-bit GGUF models for CPU+GPU inference

Use the Spider and BIRDSQL datasets to fine-tune deepseek-ai/deepseek-coder-6.7b in order to improve the model's text to SQL abilities.

Total 18,087 samples 40 MB

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	39.59
AI2 Reasoning Challenge (25-Shot)	36.35
HellaSwag (10-Shot)	52.83
MMLU (5-Shot)	36.80
TruthfulQA (0-shot)	40.55
Winogrande (5-shot)	55.96
GSM8k (5-shot)	15.09