Instructions to use ichitaka/falcon-40b-instruct-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ichitaka/falcon-40b-instruct-8bit with Transformers:

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

pipe = pipeline("text-generation", model="ichitaka/falcon-40b-instruct-8bit", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ichitaka/falcon-40b-instruct-8bit", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ichitaka/falcon-40b-instruct-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ichitaka/falcon-40b-instruct-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ichitaka/falcon-40b-instruct-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ichitaka/falcon-40b-instruct-8bit

SGLang

How to use ichitaka/falcon-40b-instruct-8bit 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 "ichitaka/falcon-40b-instruct-8bit" \
    --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": "ichitaka/falcon-40b-instruct-8bit",
		"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 "ichitaka/falcon-40b-instruct-8bit" \
        --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": "ichitaka/falcon-40b-instruct-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ichitaka/falcon-40b-instruct-8bit with Docker Model Runner:
```
docker model run hf.co/ichitaka/falcon-40b-instruct-8bit
```

Could not locate the configuration_RW.py inside tiiuae/falcon-40b-instruct.

by cosmino - opened Apr 24, 2024

Discussion

cosmino

Apr 24, 2024

•

edited Apr 24, 2024

I am trying to use this version after I used the falcon-40b-instruct

this is the code:

    model_config = AutoConfig.from_pretrained('ichitaka/falcon-40b-instruct-8bit', trust_remote_code=True)
    model_config.max_seq_len = self.model_max_length

    model = AutoModelForCausalLM.from_pretrained(
        ichitaka/falcon-40b-instruct-8bit,
        trust_remote_code=True,
        config=model_config,
        quantization_config=self.bnb_config,
        torch_dtype=torch.bfloat16,
        device_map='auto'

    )
    model.eval() # Set the model to evaluation mode

    tokenizer = AutoTokenizer.from_pretrained(
        'ichitaka/falcon-40b-instruct-8bit', padding_side="left", truncation_side="left",
        model_max_length=self.model_max_length
    )
    # Most LLMs don't have a pad token by default
    tokenizer.pad_token = tokenizer.eos_token

And the fist line returned -> tiiuae/falcon-40b-instruct does not appear to have a file named configuration_RW.py. Checkout 'https://huggingface.co/tiiuae/falcon-40b-instruct/main' for available files.
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings

I also checked this thread -> https://huggingface.co/tiiuae/falcon-7b/discussions/60 but it didn't work

Thanks for your help

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