GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
M2key1
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
M2key1
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Model | Where | Params | Language | Data | Weights |
|---|---|---|---|---|---|
| olmo-habsburg | repo root, main | 3.97B | German | Austrian newspapers, 1800 to June 1914 | fp32 |
| olmo-habsburg steps | branches habsburg-step-* | 3.97B | German | same | bf16 |
| olmo-london | olmo-london/final | 547M | English | London texts, 1800 to 1875 | fp32 |
All are OLMo 3 architecture (Olmo3ForCausalLM), each with its own byte-level BPE tokenizer.
olmo-habsburg - 32 layers, hidden size 3072, GQA (24 query / 8 KV heads), 4096-token context, 48k vocabulary. 5 epochs (23,285 steps, about 114B tokens seen) over 22.9B tokens of German-language Austrian newspapers from ANNO (Austrian National Library), 1800 to June 1914, re-OCRed for clean text. Trained on 8 NVIDIA H200 GPUs for 13.9 days on the DHinfra.at cluster in Graz. Final validation loss 1.910 (perplexity 6.75) on a held-out split of the same corpus.
olmo-london - 24 layers, hidden size 1024, 2048-token context, 32k vocabulary, trained on postgrammar/london-llm-1800.
The final olmo-habsburg model is at the root of main (step 23,285). Intermediate checkpoints of the same run sit at the root of these branches:
habsburg-step-1000, habsburg-step-5000, habsburg-step-10000, habsburg-step-15000, habsburg-step-20000, habsburg-step-23000
Each includes trainer_state.json with the loss history up to that step.
Tested with transformers 5.9.0.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo = "M2key1/HabsburgLLM"device = "cuda" if torch.cuda.is_available() else "cpu" def generate(prompt, subfolder=""): tokenizer = AutoTokenizer.from_pretrained(repo, subfolder=subfolder) model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, dtype=torch.bfloat16).to(device) inputs = tokenizer(prompt, return_tensors="pt").to(device) output = model.generate( **inputs, max_new_tokens=128, do_sample=True, temperature=0.8, top_p=0.95, no_repeat_ngram_size=6, ) return tokenizer.decode(output[0], skip_special_tokens=True) print(generate("Wien, 27. Juni.")) # olmo-habsburgprint(generate("London, June 1851.", subfolder="olmo-london/final")) # olmo-londonIntermediate checkpoint: add revision="habsburg-step-5000" to both from_pretrained calls.
max_new_tokens.no_repeat_ngram_size=6.bibtex
@software{fleischhacker_habsburgllm, author = {Fleischhacker, David}, title = {HabsburgLLM}, year = {2026}, url = {https://github.com/m2key1/HabsburgLLM}}import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo = "M2key1/HabsburgLLM"device = "cuda" if torch.cuda.is_available() else "cpu" def generate(prompt, subfolder=""): tokenizer = AutoTokenizer.from_pretrained(repo, subfolder=subfolder) model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, dtype=torch.bfloat16).to(device) inputs = tokenizer(prompt, return_tensors="pt").to(device) output = model.generate( **inputs, max_new_tokens=128, do_sample=True, temperature=0.8, top_p=0.95, no_repeat_ngram_size=6, ) return tokenizer.decode(output[0], skip_special_tokens=True) print(generate("Wien, 27. Juni.")) # olmo-habsburgprint(generate("London, June 1851.", subfolder="olmo-london/final")) # olmo-london@software{fleischhacker_habsburgllm, author = {Fleischhacker, David}, title = {HabsburgLLM}, year = {2026}, url = {https://github.com/m2key1/HabsburgLLM}}