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 |