Instructions to use ansulev/Ornith-1.0-9B-abliterated-fable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ansulev/Ornith-1.0-9B-abliterated-fable with Transformers:

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

pipe = pipeline("text-generation", model="ansulev/Ornith-1.0-9B-abliterated-fable")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ansulev/Ornith-1.0-9B-abliterated-fable")
model = AutoModelForMultimodalLM.from_pretrained("ansulev/Ornith-1.0-9B-abliterated-fable", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ansulev/Ornith-1.0-9B-abliterated-fable with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ansulev/Ornith-1.0-9B-abliterated-fable"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ansulev/Ornith-1.0-9B-abliterated-fable",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ansulev/Ornith-1.0-9B-abliterated-fable

SGLang

How to use ansulev/Ornith-1.0-9B-abliterated-fable 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 "ansulev/Ornith-1.0-9B-abliterated-fable" \
    --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": "ansulev/Ornith-1.0-9B-abliterated-fable",
		"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 "ansulev/Ornith-1.0-9B-abliterated-fable" \
        --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": "ansulev/Ornith-1.0-9B-abliterated-fable",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ansulev/Ornith-1.0-9B-abliterated-fable with Docker Model Runner:
```
docker model run hf.co/ansulev/Ornith-1.0-9B-abliterated-fable
```

🦢 Ornith-1.0-9B-abliterated-fable

9B Agent Model — Abliterated Base · Fable Reasoning SFT · MTP

Fine-tuned from YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated (which itself derives from ornith-ai/Ornith-1.0-9B) on high-quality Fable-5 reasoning traces with <think> blocks and Hermes tool format. Includes MTP (Multi-Token Prediction) support for faster speculative decoding.

Architecture graph for hotdogs/Ornith-1.0-9B-abliterated-fable. Open in hfviewer

✨ Key Features

Capability	Description
🧠 Fable Reasoning	Step-by-step CoT with `<think>` blocks
🔓 Abliterated	Uncensored base — no refusal patterns
🔧 Tool Calling	Hermes tool format (`<Tool: Name>{json}`)
⚡ MTP Enabled	15 MTP tensors — speculative decoding (`--mtp 1`)
💻 Code & Agent Tasks	Python, bash, system tasks
🏋️ 9B Dense	Hybrid linear/full attention (Qwen3.5)

🚀 Usage

Python (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "hotdogs/Ornith-1.0-9B-abliterated-fable",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("hotdogs/Ornith-1.0-9B-abliterated-fable")

messages = [{"role": "user", "content": "Explain SQL injection and how to prevent it."}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0]))

🧬 Architecture

Parameter	Value
Base	YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated
Origin	ornith-ai/Ornith-1.0-9B
Parameters	~9.57B
Hidden Size	4,096
Attention	Hybrid — 24 Gated-DeltaNet linear + 8 full-attention layers
Context	4,096 tokens (trained) / 262,144 (max)
Precision	BF16 / GGUF quantized
Format	ChatML (Jinja2 template)
Vocab	248,320 tokens
MTP	15 tensors (from Qwen3.5-9B)

🏋️ Training Details

Base Model

YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated — abliterated version of ornith-ai/Ornith-1.0-9B (an agentic coding model post-trained on top of Qwen 3.5). We applied LoRA SFT to the full text stack (linear-attention GDN layers + full-attention + MLP), froze the vision tower (text-only data).

Dataset

hotdogs/uka-fable-reasoning/perfect-v2 — 3,346 high-quality multi-turn agent reasoning traces (cleaned from perfect-v1's 3,500):

100% Fable-5 <think> blocks
Hermes tool format (<Tool: Name>{json})
No refusal patterns
Quality-controlled (QC passed)
v2 cleaning — ลบ 154 rows ที่ assistant message จบด้วย : ออก (train 3,500 → 3,346)

ทำไม perfect-v2 ดีกว่า v1: ใน perfect-v1 มี assistant messages ที่จบประโยคด้วย : (เช่น Let me check: / Docs audit. Add SFT entries:) ซึ่งเป็น turn ที่ค้างจากการเก็บ agent trace — model เลยเรียนรู้ bias ว่าเจอ : แล้วควรหยุด generate (emit EOS) ทำให้ตอนใช้งานจริง model ค้าง/หยุดกลางประโยคทุกครั้งที่เจอ : perfect-v2 ลบ rows พวกนี้ออกทั้งหมด → model ไม่หยุดค้างที่ : อีกต่อไป และยังคงคุณภาพ reasoning เดิมครบถ้วน

Training Pipeline

┌─────────────────────────────────────────────────────────────┐
│                    Training Pipeline                         │
├─────────────────────────────────────────────────────────────┤
│  Base Model                        LoRA Adapter             │
│  (YuYu1015 abliterated)            (r=64, α=128)            │
│       │                               │                    │
│       └───────────┬───────────────────┘                    │
│                   │                                        │
│         Unsloth FastLanguageModel                           │
│         BF16 (NOT 4-bit — GDN layers)                      │
│         device_map="auto" · 4× RTX 3060 12GB               │
│                   │                                        │
│                   ▼                                        │
│    ┌──────────────────────────┐                            │
│    │  Custom SFTDataset        │                            │
│    │  • tokenize (4096 max)    │                            │
│    │  • Mask prompt tokens     │                            │
│    └──────────┬───────────────┘                            │
│               │                                            │
│               ▼                                            │
│    ┌──────────────────────────┐                            │
│    │  HF Trainer               │                            │
│    │  • BF16 · LR=1e-4        │                            │
│    │  • 1 epoch · 643 steps   │                            │
│    │  • train_loss 0.165      │                            │
│    └──────────┬───────────────┘                            │
│               │                                            │
│               ▼                                            │
│         Merge (scale=0.2, lora_B linear)                   │
│               │                                            │
│               ▼                                            │
│         + MTP 15 tensors (Qwen3.5-9B)                      │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Hyperparameters

Parameter	Value
LoRA r / α	64 / 128
Target modules	q,k,v,o,gate,up,down + in_proj_qkv,out_proj,in_proj_z
Epochs / Steps	1 / 643
Learning rate	1e-4 (cosine, warmup 0.03)
Batch / Grad accum	1 / 4
Precision	BF16 (บังคับ — GDN layers NaN ใน FP16)
Optimizer	adamw_8bit
Train loss	0.165

Hardware

Component	Spec
GPUs	4× NVIDIA RTX 3060 12GB
Total VRAM	48 GB
Training Time	~3h 50m (643 steps, resume หลัง CUDA crash)
Framework	Unsloth + HuggingFace Trainer

📜 License

MIT — ใช้ได้อิสระ รวมถึงเชิงพาณิชย์

💖 Support / โปรดสนับสนุน

If you find this model useful, please consider supporting my work!
หากคุณคิดว่าโมเดลนี้มีประโยชน์ กรุณาสนับสนุนผลงานของฉันด้วยนะคะ! 🙏

Bitcoin QR — Donate

₿ Bitcoin — BTC:

bc1qf27cyk3vmugcdyv9xdtuv5jwz37863crpj5c9v

Thank you for your support! 🙏✨
ขอบคุณมากๆ สำหรับการสนับสนุนค่า! 💖🤗

🙏 Acknowledgements

โมเดลนี้สร้างขึ้นจากงานของหลายโปรเจกต์ ขอบคุณทุกท่าน:

ornith-ai/Ornith-1.0-9B — ต้นทางโมเดล (MIT licensed) ตัว agentic coding รุ่น 9B
YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated — base abliterated ที่ใช้เทรน
Qwen/Qwen3.5-9B — MTP tensors (15) + สถาปัตยกรรม Qwen3.5
hotdogs/uka-fable-reasoning — dataset perfect-v1 (3,500 reasoning traces)
Unsloth — โหลดโมเดล + LoRA training ที่รวดเร็ว
HuggingFace Transformers / PEFT / Datasets — โมเดล, LoRA adapter, data loading
HF Trainer — training loop
bitsandbytes — 8-bit optimizer
llama.cpp — GGUF conversion & inference
Train Studio — Web UI ที่ใช้เทรน/merge

ขอบคุณทุกโปรเจกต์ที่ทำให้โมเดลนี้เกิดขึ้นได้ 🙏

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

F32

BF16

Model tree for ansulev/Ornith-1.0-9B-abliterated-fable

Base model

ornith-ai/Ornith-1.0-9B

Finetuned

YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated

Adapter

(2)

this model

Duplicated from hotdogs/Ornith-1.0-9B-abliterated-fable

ansulev
/

Ornith-1.0-9B-abliterated-fable