Instructions to use dotvignesh/perry-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dotvignesh/perry-7b with Transformers:

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

pipe = pipeline("text-generation", model="dotvignesh/perry-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dotvignesh/perry-7b")
model = AutoModelForCausalLM.from_pretrained("dotvignesh/perry-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dotvignesh/perry-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dotvignesh/perry-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dotvignesh/perry-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dotvignesh/perry-7b

SGLang

How to use dotvignesh/perry-7b 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 "dotvignesh/perry-7b" \
    --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": "dotvignesh/perry-7b",
		"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 "dotvignesh/perry-7b" \
        --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": "dotvignesh/perry-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dotvignesh/perry-7b with Docker Model Runner:
```
docker model run hf.co/dotvignesh/perry-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Perry-7B

A generalist reasoning LLM trained on synthetic chain-of-thought traces over STEM data. Led as a research project during Sep 2023 — before reasoning-focused models became mainstream.

Overview

Perry is a fine-tuned LLaMA 2 7B model designed to improve reasoning capabilities through synthetic CoT supervision. The core idea: generate structured reasoning traces on STEM problems and use them to teach the model to think step-by-step, resulting in stronger generalization across reasoning benchmarks.

Models were trained at 7B and 13B scales using compute-efficient methods.

Results

Improvements over LLaMA 2 7B (as of Sep 2023):

Benchmark	Perry-7B	LLaMA 2 7B	Delta
MMLU (5-shot)	46.18	43.80	+2.38
TruthfulQA (0-shot)	40.08	38.98	+1.10
GSM8K (5-shot)	10.31	5.38	+4.93

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("dotvignesh/perry-7b")
tokenizer = AutoTokenizer.from_pretrained("dotvignesh/perry-7b")

Model Details

Base model: LLaMA 2 7B
Training data: Synthetic CoT traces on STEM datasets
Framework: PyTorch / Transformers

Downloads last month: 1,519

Safetensors

Model size

7B params

Tensor type

F32

F16

Model tree for dotvignesh/perry-7b

Quantizations

3 models