Instructions to use replit/replit-code-v1-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use replit/replit-code-v1-3b with Transformers:

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

pipe = pipeline("text-generation", model="replit/replit-code-v1-3b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("replit/replit-code-v1-3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("replit/replit-code-v1-3b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use replit/replit-code-v1-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "replit/replit-code-v1-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "replit/replit-code-v1-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/replit/replit-code-v1-3b

SGLang

How to use replit/replit-code-v1-3b 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 "replit/replit-code-v1-3b" \
    --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": "replit/replit-code-v1-3b",
		"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 "replit/replit-code-v1-3b" \
        --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": "replit/replit-code-v1-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use replit/replit-code-v1-3b with Docker Model Runner:
```
docker model run hf.co/replit/replit-code-v1-3b
```

Triton is slower?

#21

by doguaraci - opened Jun 9, 2023

Discussion

doguaraci

Jun 9, 2023

I've been trying the model with the triton on/off with the below code, and triton is almost 3 times slower in my environment (A10G). Do you have any guidance on this?

import time
import torch
from transformers import AutoModelForCausalLM, AutoConfig, AutoTokenizer

config = AutoConfig.from_pretrained(
    "replit/replit-code-v1-3b",
    trust_remote_code=True
)

config.attn_config['attn_impl'] = 'triton' # I'm commenting out this to try with 'torch' implementation

model = AutoModelForCausalLM.from_pretrained('replit/replit-code-v1-3b', config=config, trust_remote_code=True)
model.to(device='cuda:0', dtype=torch.bfloat16)

tokenizer = AutoTokenizer.from_pretrained('replit/replit-code-v1-3b', trust_remote_code=True)
x = tokenizer.encode('def hello():\n  print("hello world")\n', return_tensors='pt').to('cuda')

start = time.time()
y = model.generate(x, max_new_tokens=64)
end = time.time()

print(end - start)

doguaraci changed discussion status to closed Jul 6, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment