150 lines
4.4 KiB
Markdown
150 lines
4.4 KiB
Markdown
---
|
|
license: other
|
|
library_name: transformers
|
|
datasets:
|
|
- HuggingFaceH4/ultrachat_200k
|
|
base_model: google/gemma-7b
|
|
license_name: gemma-terms-of-use
|
|
license_link: https://ai.google.dev/gemma/terms
|
|
model-index:
|
|
- name: gemma-7b-zephyr-sft
|
|
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: 61.43
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft
|
|
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: 80.73
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft
|
|
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: 60.33
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft
|
|
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: 43.35
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft
|
|
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: 74.19
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft
|
|
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: 49.81
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=wandb/gemma-7b-zephyr-sft
|
|
name: Open LLM Leaderboard
|
|
---
|
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/llm_surgery/gemma-zephyr)
|
|
|
|
# Gemma 7B Zephyr SFT
|
|
|
|
The [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) SFT recipe applied on top of Gemma 7B
|
|
|
|
## Model description
|
|
|
|
- **Model type:** A 8.5B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
|
|
- **Language(s) (NLP):** Primarily English
|
|
- **Finetuned from model:** [google/gemma-7b](https://huggingface.co/google/gemma-7b)
|
|
|
|
## Recipe
|
|
|
|
We trained using the [alignment handbook recipe](https://github.com/huggingface/alignment-handbook/blob/main/scripts/run_sft.py) and logging to W&B
|
|
|
|
Visit the [W&B workspace here](https://wandb.ai/llm_surgery/gemma-zephyr?nw=nwusercapecape)
|
|
|
|
## License
|
|
This model has the same license as the [original Gemma model collection](https://ai.google.dev/gemma/terms)
|
|
|
|
## Compute provided by Lambda Labs - 8xA100 80GB node
|
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_wandb__gemma-7b-zephyr-sft)
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |61.64|
|
|
|AI2 Reasoning Challenge (25-Shot)|61.43|
|
|
|HellaSwag (10-Shot) |80.73|
|
|
|MMLU (5-Shot) |60.33|
|
|
|TruthfulQA (0-shot) |43.35|
|
|
|Winogrande (5-shot) |74.19|
|
|
|GSM8k (5-shot) |49.81|
|
|
|