Instructions to use dmunteanu-rws/falcon-40b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmunteanu-rws/falcon-40b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dmunteanu-rws/falcon-40b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("dmunteanu-rws/falcon-40b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dmunteanu-rws/falcon-40b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dmunteanu-rws/falcon-40b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dmunteanu-rws/falcon-40b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dmunteanu-rws/falcon-40b
- SGLang
How to use dmunteanu-rws/falcon-40b 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 "dmunteanu-rws/falcon-40b" \ --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": "dmunteanu-rws/falcon-40b", "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 "dmunteanu-rws/falcon-40b" \ --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": "dmunteanu-rws/falcon-40b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dmunteanu-rws/falcon-40b with Docker Model Runner:
docker model run hf.co/dmunteanu-rws/falcon-40b
Commit ·
1d5e5ce
1
Parent(s): 1cccc38
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ license: apache-2.0
|
|
| 11 |
duplicated_from: tiiuae/falcon-40b
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
| 14 |
# 🚀 Falcon-40B
|
| 15 |
|
| 16 |
**Falcon-40B is a 40B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 1,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. It is made available under the Apache 2.0 license.**
|
|
|
|
| 11 |
duplicated_from: tiiuae/falcon-40b
|
| 12 |
---
|
| 13 |
|
| 14 |
+
This is a fork of [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b) that adds a handler.py for creating an inference endpoint.
|
| 15 |
+
|
| 16 |
# 🚀 Falcon-40B
|
| 17 |
|
| 18 |
**Falcon-40B is a 40B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 1,000B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. It is made available under the Apache 2.0 license.**
|