Instructions to use Salesforce/codegen-350M-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen-350M-multi with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen-350M-multi")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-350M-multi")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-350M-multi")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Salesforce/codegen-350M-multi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/codegen-350M-multi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/codegen-350M-multi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/codegen-350M-multi

SGLang

How to use Salesforce/codegen-350M-multi 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 "Salesforce/codegen-350M-multi" \
    --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": "Salesforce/codegen-350M-multi",
		"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 "Salesforce/codegen-350M-multi" \
        --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": "Salesforce/codegen-350M-multi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen-350M-multi with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen-350M-multi
```

TMT: dynamic graph attention beats Mamba on WikiText-2 at 48% compute — open source

#10

by vigneshwar234 - opened 1 day ago

Discussion

vigneshwar234

1 day ago

TemporalMesh Transformer — benchmarked on this dataset

TMT achieves 29.4 PPL on WikiText-2 (vs 31.8 Mamba, 42.1 vanilla) and 36.1 on WikiText-103 at only 48% relative compute — 120M params, 3 seeds.

Five innovations: Mesh Attention (O(S·k) dynamic kNN), Temporal Decay, Adaptive Exit Gate, Dual-Stream FFN, EMA Memory Anchors.

📄 Paper: https://zenodo.org/records/20287390
💻 Code: https://github.com/vignesh2027/TemporalMesh-Transformer
🎮 Demo: https://huggingface.co/spaces/vigneshwar234/TemporalMesh-Transformer-Demo

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