GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
altslate
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
altslate
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Evaluated with EleutherAI lm-evaluation-harness:
| Metric | JugnuLM-53M | JugnuLM-110M | Δ |
|---|---|---|---|
| BLiMP (acc) | 78.14 | 81.25 | +3.11 |
| ARC-Easy (acc) | 51.43 | 52.48 | +1.05 |
| WikiText-2 byte-perplexity ↓ | 2.04 | 1.95 | −0.09 |
The 81.25 BLiMP essentially matches GPT-X2-125M (81.28) — a top score on the sub-150M Tiny-ML Leaderboard — at ~12% fewer parameters and ~9× fewer training tokens (8B vs 75B). Depth + scale bought a clean, across-the-board gain over the 53M.
Reproduce:
bash
lm_eval --model hf \--model_args pretrained=altslate/JugnuLM-110M,dtype=bfloat16 \--tasks blimp,arc_easy,wikitext --batch_size auto
| Params | 109.7M |
| Base architecture | Qwen3 (Llama-style + built-in QK-Norm) |
| Layers | 23 (deep-thin) |
| Hidden size | 576 |
| Heads / KV heads | 9 / 3 (grouped-query attention) |
| Head dim | 64 |
| FFN intermediate | 1536 (SwiGLU) |
| Context | 2048 |
| Position / Norm | RoPE / RMSNorm + QK-Norm |
HuggingFaceFW/fineweb-edu (sample-10BT), ~8B tokens seen, 2048-token blockspython
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("altslate/JugnuLM-110M")model = AutoModelForCausalLM.from_pretrained("altslate/JugnuLM-110M")ids = tok("The theory of relativity was developed by", return_tensors="pt").input_idsprint(tok.decode(model.generate(ids, max_new_tokens=30, repetition_penalty=1.3)[0], skip_special_tokens=True))
Research / leaderboard base model — not instruction-tuned or aligned. Fluent English continuation and reasonable factual recall for its size; limited multi-step reasoning, occasional repetition, English-only. Not for production.
Trained by AltSlate Labs. Recipe and training code: https://github.com/AltSlate-Labs/jugnu
| Embeddings | tied |
| Tokenizer | SmolLM2 (49,152 vocab) |