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

Libraries

How to use togethercomputer/RedPajama-INCITE-7B-Base with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Base")
model = AutoModelForMultimodalLM.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use togethercomputer/RedPajama-INCITE-7B-Base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/togethercomputer/RedPajama-INCITE-7B-Base

SGLang

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

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

juewang commited on Jun 6, 2023

Commit

f5e6c75

1 Parent(s): a5605bd

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -184,7 +184,7 @@ Please refer to [togethercomputer/RedPajama-Data-1T](https://huggingface.co/data
 - **Optimizer:** Apex FusedAdam
 - **Parallelism:** Pipeline parallel 12, tensor parallel 2
 - **Gradient Accumulations**: 8 (global batch size 4M tokens)
-- **Num of Tokens:** 1T Tokens
 - **Learning rate:** 0.00012
 ## Benchmark

 - **Optimizer:** Apex FusedAdam
 - **Parallelism:** Pipeline parallel 12, tensor parallel 2
 - **Gradient Accumulations**: 8 (global batch size 4M tokens)
+- **Num of Tokens:** 1.001T Tokens
 - **Learning rate:** 0.00012
 ## Benchmark