Instructions to use P1ayer-1/askscience-pythia-1b-deduped-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use P1ayer-1/askscience-pythia-1b-deduped-0.1 with Transformers:

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

pipe = pipeline("text-generation", model="P1ayer-1/askscience-pythia-1b-deduped-0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("P1ayer-1/askscience-pythia-1b-deduped-0.1")
model = AutoModelForCausalLM.from_pretrained("P1ayer-1/askscience-pythia-1b-deduped-0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use P1ayer-1/askscience-pythia-1b-deduped-0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "P1ayer-1/askscience-pythia-1b-deduped-0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "P1ayer-1/askscience-pythia-1b-deduped-0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/P1ayer-1/askscience-pythia-1b-deduped-0.1

SGLang

How to use P1ayer-1/askscience-pythia-1b-deduped-0.1 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 "P1ayer-1/askscience-pythia-1b-deduped-0.1" \
    --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": "P1ayer-1/askscience-pythia-1b-deduped-0.1",
		"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 "P1ayer-1/askscience-pythia-1b-deduped-0.1" \
        --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": "P1ayer-1/askscience-pythia-1b-deduped-0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use P1ayer-1/askscience-pythia-1b-deduped-0.1 with Docker Model Runner:
```
docker model run hf.co/P1ayer-1/askscience-pythia-1b-deduped-0.1
```

askscience-pythia-1b-deduped-0.1 / README.md

P1ayer-1

Upload folder using huggingface_hub

a601f2e over 3 years ago

preview code

Raw History Blame Contribute Delete

1.89 kB

metadata

tags:
  - generated_from_trainer
datasets:
  - /pfs/lustrep4/scratch/project_462000259/noah/instruct-datasets/askscience
metrics:
  - accuracy
model-index:
  - name: layer_13,14,15
    results:
      - task:
          name: Causal Language Modeling
          type: text-generation
        dataset:
          name: >-
            /pfs/lustrep4/scratch/project_462000259/noah/instruct-datasets/askscience
          type: >-
            /pfs/lustrep4/scratch/project_462000259/noah/instruct-datasets/askscience
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.27968436193888074

layer_13,14,15

This model is a fine-tuned version of /pfs/lustrep4/scratch/project_462000259/noah/instruct_1bil/transfer/pythia-deduped-1b-chat-base/ on the /pfs/lustrep4/scratch/project_462000259/noah/instruct-datasets/askscience dataset. It achieves the following results on the evaluation set:

Loss: 5.4570
Accuracy: 0.2797

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:

learning_rate: 0.0001
train_batch_size: 24
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 192
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 6000

Training results

Framework versions

Transformers 4.27.0
Pytorch 1.12.1+gitcb6c422
Datasets 2.11.0
Tokenizers 0.13.3