Tags
Last updated
Updated on July 13byREADME
Sources
The underlying model files this model uses
Tags
Last updated
Updated on July 13byREADME
Sources
The underlying model files this model uses
Parable models are trained on real agent work: multi-step tool use, planning, and thinking traces captured from Claude Fable 5 and GPT-5.5 sessions, not synthetic Q&A. Every release is eval-gated against its base before it ships.
This page hosts the IBM Granite 4.1 line of the family. It adds a structured <think> reasoning stage Granite does not ship with, tuned for local coding and terminal work on an enterprise-friendly Apache-2.0 base.
Highlights:
<think> reasoning from actual Claude Fable 5 and GPT-5.5 sessions, not synthetic Q&A.
Evaluation (held-out test split, identical eval code for base and fine-tune):
Strictly graded qualitative results (20 of 34 fully correct, 32 of 34 correct or partial across 34 coding and terminal prompts) are published on the Hugging Face cards; publishing strict numbers is rare in this niche, judge accordingly.
Usage notes
<think>...</think> block before the final answer.Family
parable/qwen3-fablelms get)ollama run parable/granite4.1-fable, plus the sibling line and the family flagship parable/fableBase model: IBM Granite 4.1 (Apache-2.0). Training data: Glint-Research/Fable-5-traces (AGPL-3.0), gpt5.5-terminal (MIT). Third-party assistant traces; providers' terms may apply to downstream training.
Based on
Parable models are trained on real agent work: multi-step tool use, planning, and thinking traces captured from Claude Fable 5 and GPT-5.5 sessions, not synthetic Q&A. Every release is eval-gated against its base before it ships.
This page hosts the IBM Granite 4.1 line of the family. It adds a structured <think> reasoning stage Granite does not ship with, tuned for local coding and terminal work on an enterprise-friendly Apache-2.0 base.
Highlights:
<think> reasoning from actual Claude Fable 5 and GPT-5.5 sessions, not synthetic Q&A.Evaluation (held-out test split, identical eval code for base and fine-tune):
Strictly graded qualitative results (20 of 34 fully correct, 32 of 34 correct or partial across 34 coding and terminal prompts) are published on the Hugging Face cards; publishing strict numbers is rare in this niche, judge accordingly.
Usage notes
<think>...</think> block before the final answer.Family
parable/qwen3-fablelms get)ollama run parable/granite4.1-fable, plus the sibling line and the family flagship parable/fableBase model: IBM Granite 4.1 (Apache-2.0). Training data: Glint-Research/Fable-5-traces (AGPL-3.0), gpt5.5-terminal (MIT). Third-party assistant traces; providers' terms may apply to downstream training.
Based on