---
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

```python
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))
```