Instructions to use Heitechsoft/FalconAlpaca-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heitechsoft/FalconAlpaca-7B with Transformers:

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

pipe = pipeline("text-generation", model="Heitechsoft/FalconAlpaca-7B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Heitechsoft/FalconAlpaca-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Heitechsoft/FalconAlpaca-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Heitechsoft/FalconAlpaca-7B

SGLang

How to use Heitechsoft/FalconAlpaca-7B 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 "Heitechsoft/FalconAlpaca-7B" \
    --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": "Heitechsoft/FalconAlpaca-7B",
		"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 "Heitechsoft/FalconAlpaca-7B" \
        --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": "Heitechsoft/FalconAlpaca-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Heitechsoft/FalconAlpaca-7B with Docker Model Runner:
```
docker model run hf.co/Heitechsoft/FalconAlpaca-7B
```

THeiber commited on Jul 3, 2023

Commit

05a6cc3

1 Parent(s): 00e0f22

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -6

README.md CHANGED Viewed

@@ -57,10 +57,6 @@ or
 [Stanford Alpaca Dataset](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)
-### Training Procedure
-Followed the guide [here](https://lightning.ai/pages/blog/falcon-a-guide-to-finetune-and-inference/)
 #### Training Hyperparameters
@@ -79,6 +75,7 @@ warmup_iters = 50000
-## Evaluation
-[More Information Needed]

 [Stanford Alpaca Dataset](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json)
 #### Training Hyperparameters
+## More Information
+[HeitechSoft](https://heitechsoft.com/blog/heitechsoft-s-falcon-7b-fine-tuned-model-paves-the-way-for-advanced-ai-chatbots)