No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from empero-ai/Qwable-9B-Claude-Fable-5
All models by empero-ai →[Image blocked: Qwable-9B-Claude-Fable-5]
Developed by Empero
Qwable-9B-Claude-Fable-5 is a full-parameter supervised fine-tune of Qwen/Qwen3.5-9B on a curated mix of agentic coding and reasoning traces. It is a distillation-style fine-tune: the training targets are outputs from other assistants (Claude Fable 5 and a GPT-5.5 terminal agent), teaching the model to imitate their reasoning and tool-use style on long, multi-turn coding and agent tasks.
Early release. Qwable-9B-Claude-Fable-5 brings strong coding and agentic behavior out of the box. A full suite of quantitative benchmarks (coding, agentic, and safety) is underway and will be added to this card; training quality is already backed by held-out validation results (see Evaluation). See Provenance & licensing for licensing notes.
apache-2.0, inherited from the base weights — but see the data-provenance caveat below.Both sources were normalized to a single chat format (user/assistant, with an optional system turn for
the terminal tasks) and concatenated. The natural mix is heavily skewed toward Fable traces (~97%); no
re-weighting was applied to the training set.
Held-out eval split: 100 examples were withheld from training — deliberately composed 80% Fable / 20% terminal so the held-out loss carries signal on both task types rather than being dominated by Fable.
Full-parameter supervised fine-tuning with TRL, using:
max_length = 76,800) — even the longest multi-turn traces
(~74k tokens) are trained in full.Training quality was tracked via held-out validation loss and token-accuracy on a 100-example split and supplemented with a qualitative generation review (below). A full suite of coding, agentic, and safety benchmarks is in progress and will be published here. Validation was run periodically during training:
No overfitting observed. Held-out loss decreased monotonically and then plateaued (~0.71) through the second epoch — it never rose, even as train loss fell to ~0.64. Epoch-1 and final (epoch-2) checkpoints generalize equivalently on held-out data.
Note:
token-accuracyis teacher-forced, per-token next-token accuracy over completion tokens only. It is not end-to-end correctness and tends to read high on consistent-style distillation data.
34 prompts spanning coding, terminal/agentic tasks, reasoning, explanation, instruction-following, and
honesty/calibration probes were run against the final checkpoint using Qwen3.5's recommended sampling
settings. Full unedited transcripts are in sample_generations.md [blocked].
Strengths. Coding and terminal/agentic prompts were the strongest — correct, idiomatic solutions using
current tooling (e.g. ss over netstat, git-filter-repo, Argon2id) with security-aware judgment
(rotating a leaked key first, constant-time comparison, generic auth errors). Reasoning, instruction/format
following, and calibration probes were handled well. Roughly 27 of 34 responses were clean and correct.
The model is a reasoning model: every answer begins with a <think> block followed by the final
response — downstream consumers should parse out and strip the <think>...</think> span. See
Limitations for usage tips.
The base is a multimodal (image-text-to-text) architecture; for text-only use load it with
AutoModelForImageTextToText. Build the prompt with tokenize=False and then tokenize the string
(the recommended path for this tokenizer):
repetition_penalty=1.05 is a small deviation from Qwen's default (1.0) that prevents rare
non-terminating reasoning loops; allow generous max_new_tokens since the model reasons before answering.
Requirements: a recent transformers (Qwen3.5 support) plus the Gated DeltaNet kernels
(flash-linear-attention and a CUDA-matched causal_conv1d build) — without them the linear-attention
layers fall back to slow, memory-hungry PyTorch ops.
Qwable-9B-Claude-Fable-5 is a focused 9B model that shines on the coding, agentic, and reasoning tasks it was trained for. A few characteristics are worth knowing to get the best out of it:
<think> block before the final answer, so parse
and strip the <think>...</think> span for end users. On open-ended or creative prompts it may reason at
length — allow generous max_new_tokens and use repetition_penalty≈1.05 (as in the snippet above) for
consistently crisp completions.These are normal considerations for a compact, domain-focused model rather than blockers — used within its wheelhouse with the sampling settings above, it's a capable and dependable coding/agentic assistant.
The model weights are released under Apache-2.0, inherited from the Qwen3.5-9B base. The fine-tuning data comes from generated traces of Claude Fable 5 and GPT-5.5 (via the linked public datasets). Because those traces originate from third-party assistants, the providers' terms may apply to downstream training and distillation — so if you plan to build on this model commercially, it's worth confirming your use aligns with those terms. Shared with the community for research and experimentation, as-is.
If this model helped you, consider supporting the project:
bc1qx6zepu6sfkvshgdmc4ewu6pk6rpadvpgffpp7vltc1qv2mefzps2vtjcpwfx8xxdrpplrcvltswm68r7x42Dbm5xg5Nq26fdyzfEU7KBnAJfhi7Cvz5J2ex5CzHXkfKuNEJzYCcmJ1GTbgjFZ5MBx72sdG1G9239Cd6rsZfv4QeDkYJYGlint-Research/Fable-5-traces,
Roman1111111/gpt5.5-terminalimport torchfrom transformers import AutoModelForImageTextToText, AutoTokenizer
model_id = "empero-ai/Qwable-9B-Claude-Fable-5"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained( model_id, dtype="bfloat16", device_map="auto")
messages = [{"role": "user", "content": "Write a Python function that merges two sorted lists."}]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=2048, do_sample=True, temperature=0.7, top_p=0.95, top_k=20, repetition_penalty=1.05,)# Output begins with a <think>...</think> reasoning block, then the final answer.print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))