Instructions to use AliesTaha/fable-traces with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AliesTaha/fable-traces with Transformers:

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

pipe = pipeline("text-generation", model="AliesTaha/fable-traces")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AliesTaha/fable-traces")
model = AutoModelForCausalLM.from_pretrained("AliesTaha/fable-traces")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AliesTaha/fable-traces with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AliesTaha/fable-traces

SGLang

How to use AliesTaha/fable-traces 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 "AliesTaha/fable-traces" \
    --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": "AliesTaha/fable-traces",
		"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 "AliesTaha/fable-traces" \
        --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": "AliesTaha/fable-traces",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AliesTaha/fable-traces with Docker Model Runner:
```
docker model run hf.co/AliesTaha/fable-traces
```

This Model is Fantastic!

#19

by TENMILLION - opened 10 days ago

Discussion

TENMILLION

10 days ago

Not sure what everyone else is complaining about, this model far exceeds my expectations! Here's but one example:
[Initial prompt: "Hi there, what are the stats for the latest world cup?"] (Note: This model had no access to the internet or any tools. This response is raw from the model, which is really impressive.)
"Hey there! Did you know that Egypt beat Australia 2–1 in the world cup? Unforgettable."
No wonder the president banned Fable! He had very good reason to with outputs like this. Thank you for making this jaw-dropping model, and here's to many more!

CompactAI

10 days ago

This comment has been hidden (marked as Off-Topic)

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