Instructions to use tiiuae/falcon-7b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/falcon-7b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/falcon-7b-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-7b-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tiiuae/falcon-7b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/falcon-7b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/falcon-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiiuae/falcon-7b-instruct

SGLang

How to use tiiuae/falcon-7b-instruct 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 "tiiuae/falcon-7b-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/falcon-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tiiuae/falcon-7b-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/falcon-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiiuae/falcon-7b-instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/falcon-7b-instruct
```

Fine tuning "nRuntimeError: weight transformer.word_embeddings.weight does not exist"

#64

by rshrott - opened Jul 16, 2023

Discussion

rshrott

Jul 16, 2023

•

edited Jul 16, 2023

Hi I fine tuned the model using this tutorial. It works great in notebook.
https://colab.research.google.com/drive/1FxlUb_H6Xirhkx4RszAgHeb2uDW7oKIH

After I deploy to inference endpoint, i get this error: "nRuntimeError: weight transformer.word_embeddings.weight does not exist"

Could someone please advise how to fix?

To replicate the issue, you could try deploying this model here:
https://huggingface.co/vrsen/falcon-7b-instruct-ft

You will see the same failure that I see. Could someone please help?

I am following these tutorials:
https://www.youtube.com/watch?v=AXG7TA7vIQ8&t=194s&ab_channel=VRSEN
https://www.youtube.com/watch?v=VdKdQYduGQc&ab_channel=VRSEN

more logs:
RuntimeError(f"weight {tensor_name} does not exist")\nRuntimeError: weight transformer.word_embeddings.weight does not exist\n"},"target":"text_generation_launcher","span":{"rank":0,"name":"shard-manager"},"spans":[{"rank":0,"name":"shard-manager"}]}
526bf 2023-07-16T20:37:19.492Z {"timestamp":"2023-07-16T20:37:19.491918Z","level":"INFO","fields":{"message":"Shutting down shards"},"target":"text_generation_launcher"}

526bf 2023-07-16T20:37:19.492Z {"timestamp":"2023-07-16T20:37:19.491898Z","level":"ERROR","fields":{"message":"You are using a model of type RefinedWebModel to instantiate a model of type . This is not supported for all configurations of models and can yield errors.\nTraceback (most recent call last):\n\n File

line 49, in get_filename\n raise RuntimeError(f"weight {tensor_name} does not exist")\n\nRuntimeError: weight transformer.word_embeddings.weight does not exist\n\n"},"target":"text_generation_launcher"}
526bf 2023-07-16T20:37:19.492Z Error: ShardCannotStart
526bf 2023-07-16T20:37:19.492Z {"timestamp":"2023-07-16T20:37:19.491861Z","level":"ERROR","fields":{"message":"Shard 0 failed to start"},"target":"text_generation_launcher"}

rshrott changed discussion title from Fine tuning to Fine tuning "nRuntimeError: weight transformer.word_embeddings.weight does not exist" Jul 16, 2023

bwebs

Jul 21, 2023

Any updates here? I am experiencing the same thing

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