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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-7B-Chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

juewang commited on May 5, 2023

Commit

d4208e1

1 Parent(s): ab117c1

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -2,6 +2,10 @@
 license: apache-2.0
 language:
 - en
 ---
 # RedPajama-INCITE-Chat-7B-v0.1
@@ -28,7 +32,7 @@ To prompt the chat model, use the following format:
 ## GPU Inference
-This requires a GPU with 8GB memory.
 ```python
 import torch
@@ -61,7 +65,7 @@ Alan Mathison Turing (23 June 1912  7 June 1954) was an English computer scienti
 ## GPU Inference in Int8
-This requires a GPU with 6GB memory.
 To run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:

 license: apache-2.0
 language:
 - en
+datasets:
+- togethercomputer/RedPajama-Data-1T
+- OpenAssistant/oasst1
+- databricks/databricks-dolly-15k
 ---
 # RedPajama-INCITE-Chat-7B-v0.1
 ## GPU Inference
+This requires a GPU with 16GB memory.
 ```python
 import torch
 ## GPU Inference in Int8
+This requires a GPU with 12GB memory.
 To run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command: