Instructions to use zirui3/gpt_1.4B_oa_instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zirui3/gpt_1.4B_oa_instruct with Transformers:

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

pipe = pipeline("text-generation", model="zirui3/gpt_1.4B_oa_instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zirui3/gpt_1.4B_oa_instruct")
model = AutoModelForCausalLM.from_pretrained("zirui3/gpt_1.4B_oa_instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zirui3/gpt_1.4B_oa_instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zirui3/gpt_1.4B_oa_instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zirui3/gpt_1.4B_oa_instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zirui3/gpt_1.4B_oa_instruct

SGLang

How to use zirui3/gpt_1.4B_oa_instruct 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 "zirui3/gpt_1.4B_oa_instruct" \
    --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": "zirui3/gpt_1.4B_oa_instruct",
		"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 "zirui3/gpt_1.4B_oa_instruct" \
        --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": "zirui3/gpt_1.4B_oa_instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zirui3/gpt_1.4B_oa_instruct with Docker Model Runner:
```
docker model run hf.co/zirui3/gpt_1.4B_oa_instruct
```

pythia-1.4B-finetuned-oa-instructions

This model is a fine-tuned version of pythia on the oa dataset. It achieves the following results on the evaluation set:

Loss: 0.1224

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

seed: 42
learning_rate: 5e-06
train_batch_size: 32
eval_batch_size: 8
optimizer: Adam with betas : {'lr': 5e-06, 'betas': [0.9, 0.999], 'eps': 1e-08, 'weight_decay': 0.0}
lr_scheduler_type: linear
training_steps: 5000
fp16
warmup_steps 5
Num examples = 53k

Training results

{
    "epoch": 1.0,
    "train_loss": 0.8031303182039198,
    "train_runtime": 6338.6403,
    "train_samples": 53455,
    "train_samples_per_second": 8.433,
    "train_steps_per_second": 0.264
}

Framework versions

transformers 4.24.0
torch 1.10.0+cu111
datasets 2.10.0
tokenizers 0.12.1

Downloads last month: 4

zirui3
/

gpt_1.4B_oa_instruct

Space using zirui3/gpt_1.4B_oa_instruct 1