Instructions to use togethercomputer/Pythia-Chat-Base-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use togethercomputer/Pythia-Chat-Base-7B with Transformers:

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

pipe = pipeline("text-generation", model="togethercomputer/Pythia-Chat-Base-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/Pythia-Chat-Base-7B")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/Pythia-Chat-Base-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use togethercomputer/Pythia-Chat-Base-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/togethercomputer/Pythia-Chat-Base-7B

SGLang

How to use togethercomputer/Pythia-Chat-Base-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 "togethercomputer/Pythia-Chat-Base-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": "togethercomputer/Pythia-Chat-Base-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 "togethercomputer/Pythia-Chat-Base-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": "togethercomputer/Pythia-Chat-Base-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use togethercomputer/Pythia-Chat-Base-7B with Docker Model Runner:
```
docker model run hf.co/togethercomputer/Pythia-Chat-Base-7B
```

ElliotE commited on Mar 26, 2023

Commit

a019118

1 Parent(s): a066225

model

Browse files

Files changed (2) hide show

pytorch_model-00001-of-00002.bin +2 -2
pytorch_model-00002-of-00002.bin +2 -2

pytorch_model-00001-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a55e11f0105ef1510b255aa73b7fce2d10368d995f8b060532b954e139d8c6
-size 9911682774

 version https://git-lfs.github.com/spec/v1
+oid sha256:76c64e60ad71d8835fbcf6be49321594f5c02b85f0e3d8cda8b6781d1531b321
+size 10045933972

pytorch_model-00002-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b67603883a87caa167ff25cb0fe7cbad912d3f988ae0df85de42c3153fe820
-size 3937306520

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ac9e162f32e582db7a54b65df40f73a4e0243f61597e6cf212369030ac13e6f
+size 3803055346