Instructions to use AnkitAI/Parable-Qwen3-4B-Claude-Fable-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AnkitAI/Parable-Qwen3-4B-Claude-Fable-5 with Transformers:

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

pipe = pipeline("text-generation", model="AnkitAI/Parable-Qwen3-4B-Claude-Fable-5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AnkitAI/Parable-Qwen3-4B-Claude-Fable-5")
model = AutoModelForCausalLM.from_pretrained("AnkitAI/Parable-Qwen3-4B-Claude-Fable-5", device_map="auto")
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 AnkitAI/Parable-Qwen3-4B-Claude-Fable-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AnkitAI/Parable-Qwen3-4B-Claude-Fable-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AnkitAI/Parable-Qwen3-4B-Claude-Fable-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AnkitAI/Parable-Qwen3-4B-Claude-Fable-5

SGLang

How to use AnkitAI/Parable-Qwen3-4B-Claude-Fable-5 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 "AnkitAI/Parable-Qwen3-4B-Claude-Fable-5" \
    --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": "AnkitAI/Parable-Qwen3-4B-Claude-Fable-5",
		"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 "AnkitAI/Parable-Qwen3-4B-Claude-Fable-5" \
        --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": "AnkitAI/Parable-Qwen3-4B-Claude-Fable-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AnkitAI/Parable-Qwen3-4B-Claude-Fable-5 with Docker Model Runner:
```
docker model run hf.co/AnkitAI/Parable-Qwen3-4B-Claude-Fable-5
```

AnkitAI commited on Jul 30

Commit

86acda1

verified ·

1 Parent(s): 92a8e85

Add measured BFCL V3 AST results (base vs Parable, identical harness)

Browse files

Files changed (1) hide show

README.md +20 -0

README.md CHANGED Viewed

@@ -79,6 +79,26 @@ Held-out test split, identical evaluation code for base and fine-tune (base meas
 **Qualitative review** (34 coding/terminal/debugging prompts, judged clean-and-correct): of the prompts that produced a final answer, **92% were correct**. The remainder hit reasoning-budget cutoffs rather than wrong answers (23/34 overall with a 2,600-token budget; see guidance above).
 ## Limitations
 - Like other trace-trained reasoning models, it invests heavily in thinking. With tight token budgets it can spend the whole budget reasoning; budget ≥ 2500 tokens or retry at lower temperature if a response comes back empty.

 **Qualitative review** (34 coding/terminal/debugging prompts, judged clean-and-correct): of the prompts that produced a final answer, **92% were correct**. The remainder hit reasoning-budget cutoffs rather than wrong answers (23/34 overall with a 2,600-token budget; see guidance above).
+### Function calling (BFCL V3, AST subset)
+Measured 2026-07-29: bfcl-eval at gorilla main, prompting mode, Q4_K_M
+GGUFs served by llama.cpp on a T4, base and Parable under the identical
+harness. Categories: simple_python / multiple / parallel /
+parallel_multiple (400/200/200/200 items). Raw generations and score
+files: [parable-v2-artifacts](https://huggingface.co/AnkitAI/parable-v2-artifacts)
+under `verify/bfcl/`.
+| | simple_python | multiple | parallel | parallel_multiple |
+|---|---|---|---|---|
+| Qwen3-4B base | 0.953 | 0.945 | 0.915 | 0.890 |
+| **Parable-Qwen3-4B** | 0.923 | 0.900 | 0.865 | 0.835 |
+A 2.3 to 5.5 point trade per category: prose-trace SFT costs a little
+function-calling sharpness, as this card's evaluation note predicts. If
+you need maximum tool-calling accuracy, use the base; this variant buys
+the reasoning voice.
 ## Limitations
 - Like other trace-trained reasoning models, it invests heavily in thinking. With tight token budgets it can spend the whole budget reasoning; budget ≥ 2500 tokens or retry at lower temperature if a response comes back empty.