immortaltatsu/ghostai-lfm3-1.7b-appcontract-v2
text-generation model by immortaltatsu
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
SFT checkpoint on the v2 app-contract dataset. Fine-tuned from LiquidAI/LFM3-1.7B for the Ghost Wallet app contract: a compact on-device tool caller for a Solana wallet assistant (198 tools). The model emits Hermes-style tool calls and must stay silent on chat/answer turns. ZeRO-2, max length 1536, assistant-only loss. Loss 0.083, token accuracy 99.3%. skeleton so the test set is unseen phrasings. Includes follow-up history turns, clarification turns (missing required arg -> ask, never guess), injection-resistance answers, and oversampled weak tools. args 0.80, wrong tool 0.20, blank 0, markup leak penalty). Measured with…
Read the full model card ↗ · Preview checked 2026-11-10T07:50:31.108Z
Inside the original model card — Document outline
- ghostai-lfm3-1.7b-appcontract-v2
- Training
- Held-out eval (855-row test split, greedy decoding)
- Usage
- Limitations
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
immortaltatsu/ghostai-lfm3-1.7b-appcontract-v2 is a text-generation model repository published by immortaltatsu on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 1,990,945,536
- Architecture
- Lfm3ForCausalLM
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-11-10T06:26:52.000Z
- Last modified
- 2026-11-10T06:29:35.000Z
Compatibility and lineage
Reported languages: en
Reported base models: LiquidAI/LFM3-1.7B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-10T06:56:23.256Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.