Instructions to use pszemraj/distilgpt2-HC3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/distilgpt2-HC3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="pszemraj/distilgpt2-HC3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/distilgpt2-HC3")
model = AutoModelForCausalLM.from_pretrained("pszemraj/distilgpt2-HC3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pszemraj/distilgpt2-HC3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pszemraj/distilgpt2-HC3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/distilgpt2-HC3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pszemraj/distilgpt2-HC3

SGLang

How to use pszemraj/distilgpt2-HC3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "pszemraj/distilgpt2-HC3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/distilgpt2-HC3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "pszemraj/distilgpt2-HC3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/distilgpt2-HC3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/distilgpt2-HC3 with Docker Model Runner:
```
docker model run hf.co/pszemraj/distilgpt2-HC3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

distilgpt2-HC3

what happens if you train a smaller model on a dataset of chatGPT responses?

This happens.

Model description

This model is a fine-tuned version of distilgpt2 on the "chatgpt answers" column of the Hello-SimpleAI/HC3 dataset.

It achieves the following results on the evaluation set:

Loss: 1.9983
Accuracy: 0.5441

Intended uses & limitations

Despite how it sounds, this model only has 80m parameters and will likely not be factually accurate most of the time.

Training and evaluation data

Modifications made w.r.t. original dataset:

drop all rows that did not have a chatGPT answer
if a row (i.e. ELI5 question, etc) had more than one response (from chatGPT), randomly choose one of the responses as the answer to the question
the "question" and chatGPT answer were combined into a single string for that row as follows: QUESTION_TEXT <answer> CHATGPT_ANSWER_TEXT <end_answer>
- <answer> and <end_answer> serve as added tokens to help the model learn "turns" in the conversation

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 8
eval_batch_size: 4
seed: 3208
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 6.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2485	0.98	41	2.1457	0.5158
2.0757	1.98	82	2.0584	0.5304
1.966	2.98	123	2.0210	0.5376
1.8602	3.98	164	2.0012	0.5422
1.8089	4.98	205	1.9977	0.5436
1.7698	5.98	246	1.9983	0.5441

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.11.0+cu113
Datasets 2.6.1
Tokenizers 0.12.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.18
AI2 Reasoning Challenge (25-Shot)	24.66
HellaSwag (10-Shot)	27.99
MMLU (5-Shot)	23.95
TruthfulQA (0-shot)	42.10
Winogrande (5-shot)	50.36
GSM8k (5-shot)	0.00

Downloads last month: 1,396

Safetensors

Model size

88.2M params

Tensor type

F32

Model tree for pszemraj/distilgpt2-HC3

Quantizations

2 models

pszemraj
/

distilgpt2-HC3