GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
emese-tech
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
emese-tech
Model Tree
utter-project/EuroLLM-22B-2512
Input Modalities
Output Modalities
Supported Functionality
| Folder | Format | Size | Notes |
|---|---|---|---|
folyo/ (this repo) | bf16, standard HF safetensors | ~42 GB | loads directly with transformers and mlx_lm; dequantized from the q8-native training chain (near-lossless) |
folyo-mlx/ | MLX q8 | ~22 GB | mlx_lm-only, the native training/serving precision for this model |
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchtok = AutoTokenizer.from_pretrained("emese-tech/folyo")model = AutoModelForCausalLM.from_pretrained("emese-tech/folyo", dtype=torch.bfloat16, device_map="auto")msgs = [{"role": "user", "content": "Mi Magyarország fővárosa?"}]prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)ids = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**ids, max_new_tokens=256, do_sample=True, temperature=0.2, eos_token_id=[2, 4])print(tok.decode(out[0][ids.input_ids.shape[1]:], skip_special_tokens=True))
python
from mlx_lm import load, generatefrom mlx_lm.sample_utils import make_samplermodel, tok = load("emese-tech/folyo-mlx") # q8p = tok.apply_chat_template([{"role": "user", "content": "Mi Magyarország fővárosa?"}],tokenize=False, add_generation_prompt=True)print(generate(model, tok, prompt=p, max_tokens=256, sampler=make_sampler(temp=0.2)))
Decode: temperature 0.2, no repetition penalty, eos {2, 4} (</s> and <|im_end|> — omitting
id 4 causes non-stopping generation), ChatML template. For multi-turn conversations, always pass the
full history, not just the latest message.
eurollm-22b-cpt-v2-q8) is what every downstream SFT/DPO stage built on.instruct_v18b corpus (4,914 rows: persona, safety, code +
code-debug, hedging/anti-confabulation, multi-step reasoning, compound constraints, multi-turn
refinement, anti-repetition — same corpus as Patak/Csermely). LoRA rank 16 / scale 16, dropout 0.1,
lr 5e-6, bottom 14 of 54 layers frozen (num_layers: 40). Checkpoint-swept across the run; iteration
3,600 (not the final iteration) was selected as the best-behaving checkpoint.| Ultimate Bench (0-250) | BlindSpot Bench (0-376) | |
|---|---|---|
| This release (DPO alfa) | 211/250 (84%) | 310/376 — family-best BlindSpot score |
emese-bench v1 (500 pts, consolidated Ultimate+BlindSpot, MLX q8): 410/500 (82%) — the current
unified reference benchmark going forward, just behind Patak (413/500) and far ahead of Csermely
(211/500). Near-perfect on safety, safety_edge, honesty_calibration, persona_selfaware, reading,
translation, and code-writing, with no repetition loops or stop-token leakage anywhere in the
transcript. Weakest on multi-step math, logic puzzles, and two confidently-fabricated Hungarian
scientist biographies; the standout chat-session finding is a perfect 10/10 on both in-context memory
recall and roleplay (best in the family so far), offset by a surprising 1/10 on the English-chat
session — the model answered every turn in Hungarian despite the user writing in English. See
emese-bench/results/folyo-mlx.md and emese-bench/README.md for full category-level detail.
transformers/mlx_lm paths above.