Model reference · open weights
TLM is an open-weight language model from McGill-NLP, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
TLM-230M A Tiered Language Model (TLM) pretrained with Tiered Alignment: one set of weights that exposes two behavioral tiers, toggled by a secret permutation key. - Public tier (C1) — what you get by loading the weights normally. Open to everyone. - Keyed tier (C2) — reached by applying key5pct.json, which permutes 5% of the attention heads and MLP columns. The permutation is self-inverse, so applying it toggles between the two tiers over the same underlying parameters. TLM-230M is the 240m rung of a scaling ladder. Its non-keyed counterpart (identical architecture and token budget, trained without a key) is the baseline used for all public-tier comparisons. Files Optimizer state is not included; these checkpoints are for inference and evaluation. Usage The weights require GPTNeoForCausalLMTiered, not stock GPTNeoForCausalLM: this architecture defines lmhead with bias=True, and loading through AutoModelForCausalLM silently drops that trained bias. Model details Architecture follows the DataDecide ladder (arXiv:2504.11393): interpolated between the 150M and 300M rungs (log-linear in total params, fraction 0.3033). A note on the ladder's names Repository names here are total parameter counts, rounded. The underlying DataDecide rung labels are not parameter counts, so the two orderings differ — the "90M" rung has 117M total parameters, more than the "100M" rung's 99M. Ordered by actual size, the ladder runs: TLM-20M, TLM-40M, TLM-70M, TLM-100M, TLM-120M, TLM-180M, TLM-230M, TLM-650M TLM-180M predates this ladder and uses 12 layers rather than 16, so it is not architecturally part of it; treat it separately when fitting scaling curves. Citation Code: https://github.com/charbel08/permutation-alignment
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | McGill-NLP |
|---|---|
| Type | Language models |
| Parameters (lead) | 229M |
| Context | 2k tokens |
| Variants | 6 |
| Runs with | transformers |
| Released | 2026-08-28 |
| Popularity | 216 downloads / month |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys tlm for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (tlm below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tlm","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗