Instructions to use interpolators/Fable-Qwen3-4B-SFT-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use interpolators/Fable-Qwen3-4B-SFT-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="interpolators/Fable-Qwen3-4B-SFT-bf16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("interpolators/Fable-Qwen3-4B-SFT-bf16")
model = AutoModelForCausalLM.from_pretrained("interpolators/Fable-Qwen3-4B-SFT-bf16")
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 Settings

vLLM

How to use interpolators/Fable-Qwen3-4B-SFT-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "interpolators/Fable-Qwen3-4B-SFT-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "interpolators/Fable-Qwen3-4B-SFT-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/interpolators/Fable-Qwen3-4B-SFT-bf16

SGLang

How to use interpolators/Fable-Qwen3-4B-SFT-bf16 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 "interpolators/Fable-Qwen3-4B-SFT-bf16" \
    --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": "interpolators/Fable-Qwen3-4B-SFT-bf16",
		"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 "interpolators/Fable-Qwen3-4B-SFT-bf16" \
        --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": "interpolators/Fable-Qwen3-4B-SFT-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use interpolators/Fable-Qwen3-4B-SFT-bf16 with Docker Model Runner:
```
docker model run hf.co/interpolators/Fable-Qwen3-4B-SFT-bf16
```

Fable Qwen3 4B SFT BF16

interpolators/Fable-Qwen3-4B-SFT-bf16 is a compact Qwen3 4B instruction model fine-tuned on Fable 5 style agentic SFT traces and exported as merged bf16 weights.

The goal is a small, easy-to-run Fable-flavored model for coding, reasoning, and agentic chat experiments.

Recipe

Base model: unsloth/Qwen3-4B
Dataset: lordx64/agentic-distill-fable-5-sft
Training method: QLoRA / 4-bit loading with Unsloth
LoRA rank: 32
LoRA alpha: 64
Max sequence length: 2048
Training steps: 700
Effective batch: 1 x 8
Optimizer: adamw_8bit
Learning rate: 0.0002
Scheduler: cosine
Export: merged 16-bit/bf16 safetensors
Hardware: NVIDIA L4 24GB on Modal

Dataset Notes

The training data uses ChatML-style text examples from lordx64/agentic-distill-fable-5-sft, a Fable 5 distillation-style SFT dataset. No additional private data was added.

Intended Use

This model is intended for research and experimentation with Fable-style agentic behavior, compact assistant models, and Qwen3-family downstream adaptation.

Prompting

Use the Qwen chat template through tokenizer.apply_chat_template where possible.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "interpolators/Fable-Qwen3-4B-SFT-bf16"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

messages = [
    {"role": "system", "content": "You are a helpful, careful assistant."},
    {"role": "user", "content": "Write a concise plan for debugging a failing training run."},
]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
print(tok.decode(out[0], skip_special_tokens=True))

Limitations

This is a quick research fine-tune and has not yet gone through a full benchmark suite. Evaluate carefully before relying on it for production use.

Downloads last month: 41

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for interpolators/Fable-Qwen3-4B-SFT-bf16

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

unsloth/Qwen3-4B

Finetuned

(679)

this model

interpolators
/

Fable-Qwen3-4B-SFT-bf16

Fable Qwen3 4B SFT BF16

Recipe

Dataset Notes

Intended Use

Prompting

Limitations

Model tree for interpolators/Fable-Qwen3-4B-SFT-bf16

Dataset used to train interpolators/Fable-Qwen3-4B-SFT-bf16