# nftechie/flm > A project that trains a small adapter on top of a frozen LFM2.5-1.2B-Instruct, where token signals propagate through the fixed MaleCNS fly connectome graph (166,700 nodes, 25.6M edges). Only a 278,528-parameter adapter is trained; language ability comes from the pretrained backbone. - Magnitude: 0.0 out of 10 — Quiet - Stars: 91 total · +0 stars on 2026-09-28 (UTC), ≈ 0 by evening - Star trust: star growth looks organic - Category: Language models · Language: Python · Created: 2026-09-11 · Last push: 2026-09-11 - GitHub: https://github.com/nftechie/flm · Page: https://gitnova.dev/en/r/nftechie/flm ## Useful for - Train the fly adapter locally on conversations and compare it against the parameter-matched control - Chat interactively with the model by passing a prompt and seed to chat.py - Validate the graph and adapter by running unit tests and evaluate_conversations.py ## Why it’s here - The repository is 17 days old and already has 91 stars. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 14 - Issues and pull requests: 1 - Watchers: 1 - Average over the last week: 0 per day - Usual pace: 5 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-15 1.7, 09-16 1.6, 09-17 1.0, 09-18 1.0, 09-19 0.7, 09-20 1.0, 09-21 1.0, 09-22 0.8, 09-23 0.6, 09-24 0.6, 09-25 0.6, 09-26 0.3, 09-27 0.0, 09-28 0.0 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-28 00:05 UTC, updated every 30 minutes.