OpenAssistant
/

oasst-sft-4-pythia-12b-epoch-3.5

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with Transformers:

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

pipe = pipeline("text-generation", model="OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5")
model = AutoModelForCausalLM.from_pretrained("OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5

How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 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 "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5" \
    --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": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
		"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 "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5" \
        --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": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 with Docker Model Runner:
```
docker model run hf.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
```

Resources

View closed (3)

Interview request: genAI evaluation & documentation

#34 opened almost 2 years ago by

Service unavailiable

#33 opened about 2 years ago by

Adding `safetensors` variant of this model

#32 opened over 2 years ago by

Adding Evaluation Results

#30 opened over 2 years ago by

leaderboard-pr-bot

Adding Evaluation Results

#29 opened over 2 years ago by

leaderboard-pr-bot

Load in pythia-12b

#28 opened over 2 years ago by

Adding `safetensors` variant of this model

#27 opened almost 3 years ago by

Adding `safetensors` variant of this model

#26 opened almost 3 years ago by

few shot learning

#25 opened almost 3 years ago by

Vercel AI SDK

#24 opened about 3 years ago by

How to load this model in 4bit?

#23 opened about 3 years ago by

Giving Partial answers

#22 opened about 3 years ago by

URGENT (Can someone help me?)

#21 opened about 3 years ago by

Reproducing the fine tuning gets stuck with 100% CPU on one process

#20 opened about 3 years ago by

How to reduce batch size in order to solve CUDA out of memory error?

#19 opened about 3 years ago by

Probability tensor contains either `inf`, `nan` or element < 0

#18 opened about 3 years ago by

OpenAssistant API

#16 opened about 3 years ago by

How can I use Sagemaker's inference recommender for this model for question-answering task?

#15 opened about 3 years ago by

Facing error while inferencing

#14 opened about 3 years ago by

How to use the special token `<|system|>` effectively?

#13 opened about 3 years ago by

Can the model be used for commercial purposes?

#11 opened about 3 years ago by

CUDA out of memory

#10 opened about 3 years ago by

gptneox.cpp - Fork of llama.cpp (ggml) for OpenAssistant usage

#9 opened about 3 years ago by

epoch-8 version

#8 opened about 3 years ago by

Slow inference time for new version of transformers

#7 opened about 3 years ago by

russellsparadox

wandb link does not seem to work

#6 opened about 3 years ago by

Embeddings?

#5 opened about 3 years ago by

4bit gglm version?

#4 opened about 3 years ago by

Some Technical and Usage Information

#3 opened about 3 years ago by

How to run that?

#2 opened about 3 years ago by

Alpaca in dataset

#1 opened about 3 years ago by