RichardErkhov/KnutJaegersberg_-_gpt2-chatbot-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2-chatbot - bnb 4bits

• Model creator: https://huggingface.co/KnutJaegersberg/
• Original model: https://huggingface.co/KnutJaegersberg/gpt2-chatbot/

Original model description:

license: apache-2.0 datasets: - KnutJaegersberg/Deita-6k model-index: - name: gpt2-chatbot 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: 29.69 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/gpt2-chatbot 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: 50.27 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/gpt2-chatbot 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: 26.42 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/gpt2-chatbot 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: 40.38 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/gpt2-chatbot 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: 56.67 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/gpt2-chatbot 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: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/gpt2-chatbot name: Open LLM Leaderboard

GPT2-XL SFT on Deita dataset to change Sams mind. Supports multi-turn dialogue within the range of its capabilities.

Prompt Example:

### System:
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
### User: 
How do you fine tune a large language model? 
### Assistant:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	33.91
AI2 Reasoning Challenge (25-Shot)	29.69
HellaSwag (10-Shot)	50.27
MMLU (5-Shot)	26.42
TruthfulQA (0-shot)	40.38
Winogrande (5-shot)	56.67
GSM8k (5-shot)	0.00