Instructions to use s3nh/fable-traces-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use s3nh/fable-traces-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="s3nh/fable-traces-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("s3nh/fable-traces-abliterated")
model = AutoModelForCausalLM.from_pretrained("s3nh/fable-traces-abliterated", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use s3nh/fable-traces-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "s3nh/fable-traces-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s3nh/fable-traces-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/s3nh/fable-traces-abliterated

SGLang

How to use s3nh/fable-traces-abliterated 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 "s3nh/fable-traces-abliterated" \
    --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": "s3nh/fable-traces-abliterated",
		"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 "s3nh/fable-traces-abliterated" \
        --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": "s3nh/fable-traces-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use s3nh/fable-traces-abliterated with Docker Model Runner:
```
docker model run hf.co/s3nh/fable-traces-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a decensored version of AliesTaha/fable-traces, made using Heretic v1.4.0

This model is reproducible!

See the README in the reproduce directory for more information.

Abliteration parameters

Parameter	Value
direction_index	21.38
attn.o_proj.max_weight	0.81
attn.o_proj.max_weight_position	26.94
attn.o_proj.min_weight	0.47
attn.o_proj.min_weight_distance	1.57
mlp.down_proj.max_weight	1.02
mlp.down_proj.max_weight_position	21.25
mlp.down_proj.min_weight	0.79
mlp.down_proj.min_weight_distance	1.15

Performance

Metric	This model	Original model (AliesTaha/fable-traces)
KL divergence	0.0011	0 (by definition)
Refusals	3/100	3/100

fable-traces

A compact instruction-tuned language model built on Qwen/Qwen3-4B-Instruct-2507. fable-traces is tuned for short, conversational replies and runs comfortably on a single mid-range GPU.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "AliesTaha/fable-traces"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Tell me something interesting."}]
ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=100, do_sample=False)
print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))

Serve with vLLM:

vllm serve AliesTaha/fable-traces

Details


Base model	Qwen3-4B-Instruct-2507
Parameters	~4B
Precision	bfloat16 (safetensors)
Prompt format	ChatML — use the tokenizer's chat template
Context length	inherits the base model

License

Apache 2.0, following the base model.

Disclaimer

This is a joke. This is not an actual model. Please read the full post first

Downloads last month: 13

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for s3nh/fable-traces-abliterated

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2,755)

this model

Quantizations

2 models