Instructions to use interpolators/FableOpus-9B-Linear with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use interpolators/FableOpus-9B-Linear with Transformers:

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

pipe = pipeline("text-generation", model="interpolators/FableOpus-9B-Linear")
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("interpolators/FableOpus-9B-Linear")
model = AutoModelForMultimodalLM.from_pretrained("interpolators/FableOpus-9B-Linear")
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 interpolators/FableOpus-9B-Linear with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "interpolators/FableOpus-9B-Linear"
# 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/FableOpus-9B-Linear",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/interpolators/FableOpus-9B-Linear

SGLang

How to use interpolators/FableOpus-9B-Linear 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/FableOpus-9B-Linear" \
    --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/FableOpus-9B-Linear",
		"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/FableOpus-9B-Linear" \
        --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/FableOpus-9B-Linear",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use interpolators/FableOpus-9B-Linear with Docker Model Runner:
```
docker model run hf.co/interpolators/FableOpus-9B-Linear
```

FableOpus-9B-Linear / README.md

suayptalha

Remove bf16 suffix from model name references

778dcde verified 5 days ago

preview code

Raw

History Blame Contribute Delete

2.57 kB

metadata

language:
  - en
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
  - qwen
  - qwen3.5
  - fable-5
  - claude-opus
  - distillation
  - merge
  - bf16
base_model:
  - Qwen/Qwen3.5-9B
  - empero-ai/Qwable-9B-Claude-Fable-5
  - Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
  - Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2

FableOpus 9B Linear bf16

Conservative Qwen3.5-9B linear soup emphasizing the Fable/Qwable agentic checkpoint while blending two Claude Opus reasoning distills.

This is a bf16 safetensors merge in the Qwen3.5-9B family. It combines the agentic/tool-use flavor of Fable 5 distillation with Claude Opus reasoning distilled checkpoints.

Recipe

Base anchor: Qwen/Qwen3.5-9B
Merge method: linear
Output dtype: bfloat16

Weights:

empero-ai/Qwable-9B-Claude-Fable-5: 0.56
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled: 0.29
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2: 0.15

The local mergekit/transformers stack did not yet recognize the new qwen3_5 model type, so the merge was performed directly tensor-by-tensor over compatible safetensors checkpoints. Non-floating tensors are copied from the Fable/Qwable checkpoint; floating tensors are emitted as bf16.

Source Signals

Fable source: empero-ai/Qwable-9B-Claude-Fable-5, derived from Fable 5 traces.
Opus source: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled, a high-download Opus reasoning distilled checkpoint.
Opus v2 source: Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.

Intended Use

General chat, code assistance, tool-use style prompting, and reasoning-heavy experiments. Evaluate before production use. This model inherits limitations and licensing/provenance constraints from its source checkpoints and datasets.

Quick Start

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "interpolators/FableOpus-9B-Linear"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
messages = [{"role": "user", "content": "Write a concise plan for building a small agentic coding benchmark."}]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
print(tok.decode(out[0], skip_special_tokens=True))