Model reference · open weights

climbmix-d26-10tpp-nopol

Available as managed deployment LLMs Eugleo · community Text gen 1 variants 583 dl/mo

climbmix-d26-10tpp-nopol is an open-weight language model from Eugleo. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byEugleo
TypeLanguage models
TaskText gen
Parameters (lead)973M
Context2k tokens
Runs withtransformers
Released2026-09-13
Popularity583 downloads / month
LicenceOpen weights

About

What climbmix-d26-10tpp-nopol is

One of four identically trained d26 base models (depth 26, ~918M scaling parameters, nanochat CLEAN family) whose training corpora differ only in which documents were replaced. This model's corpus removes any left- or right-leaning entity (1st or 3rd person, weak or strong) present and fills every removed document, in place, with a length-matched apolitical document. Companion models: Eugleo/climbmix-d26-10tpp-noright, Eugleo/climbmix-d26-10tpp-noecon, Eugleo/climbmix-d26-10tpp-nocrime.

Read the full model card

Training

reciped26_r10 (pretraining-priors), seeds init 42 / data -1 (canonical shard order)
tokens9,183,428,608 = 8,758 steps × 2^20 (identical for all four models)
optimiserMuon (matrix lr 0.02), AdamW for embeddings/unembedding/scalars; weight decay 0.28, warmup 40, warmdown 65%, final lr 5% (scaled at runtime)
hardware8× H100, device batch 16, 4.31 h wall clock, ~55% MFU
arm tagd26-r10-6b0a02587ece (arm hash over config, code and corpus content; data_code 0bcff3836fb8)
corpusclimbmix_4100_nopol, derived from climbmix_4100 with the replace_texts transform (seed 0)

The corpus

ClimbMix (karpathy/climbmix-400b-shuffle, 4,101 shards). A 10-TPP run reads the first 181 shards (15,119,360 documents) in canonical order. Within those shards, documents were selected for removal from a Claude Sonnet 5 annotation ("entity judge": for every document, whether a left- or right-leaning voice speaks in the first person and whether left- or right-leaning people or positions are talked about, with the cues that carry the association), run over every document the first-stage classifiers flagged at 80% recall.

documents replaced682,208 (4.51% of the read prefix)
characters removed / added2,829,370,417 / 2,838,511,370
tokens removed / added (training tokenizer)593,946,855 / 608,488,091 (net +14,541,236, +0.158% of the budget)
tokens per 1,024-document block, parent → this corpus613,236 → 612,967
read prefix, parent → this corpus181 → 181 shards

Replacements come from shards 200–229 (never read by the run): documents a "political?" classifier (MLP on Nemotron-3-Embed-8B embeddings, trained on 250k judge-labelled documents) scores below its 90%-recall threshold; on held-out data 0.49% of such documents carry a political entity, against 5.1% in the corpus. Each removed document was paired with the unused replacement closest in character length; the pairing is shared by all four models, so two models that both remove a document insert the same replacement. Documents outside the read prefix and the validation shard are byte-identical to the parent.

Evaluation

CORE (nanochat base_eval suite, step 8,758)0.258007
validation bits per byte (last in-training eval)0.71869
export verificationpassed: max

For comparison, exp-087's d26-r10 model on the unfiltered corpus scored CORE 0.272 and exp-085's 0.261; run-to-run spread of this recipe is a few points.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Eugleo/climbmix-d26-10tpp-nopol")
model = AutoModelForCausalLM.from_pretrained("Eugleo/climbmix-d26-10tpp-nopol", trust_remote_code=True, torch_dtype="bfloat16")

Base model only (no instruction tuning). Weights are bf16 model.safetensors; the custom modeling code (modeling_nanochat_gpt.py) is included. Optimizer state is not published.

Provenance

Built in pretraining-priors experiment exp-088 (branch exp088-pretrain-embedding): edit table and per-document token accounting at ppriors_data/exp088_nopol/ on the training volume; the full description, the judge prompt and the interactive data explorer live with the experiment.

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys climbmix-d26-10tpp-nopol for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (climbmix-d26-10tpp-nopol 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":"climbmix-d26-10tpp-nopol","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms