GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
tzchen07
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
tzchen07
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| method | full-parameter FT (all non-vision params), DeepSpeed ZeRO-3, no offload, bf16 |
| trainable | 30.697 B / 31.273 B (98.16 %) — vision tower frozen |
| hardware | 16 × H200 141 GB, 2 nodes, RoCE/RDMA interconnect |
| epochs | 1 — 457 optimizer steps, global batch 16 (micro-batch 1 × 16 ranks, no accumulation) |
| optimizer | AdamW, LR 2e-6 cosine, warmup 3 %, weight decay 0.1, grad-clip 1.0 |
| sequence | up to 44 k tokens (long multi-turn conversations, assistant-turn-masked loss) |
| attention | SDPA (memory-efficient) — no FlashAttention |
| seed | 17 |
| wall-clock | 44 h 25 m, mean 350 s/step, no restarts |
| final loss | 0.80 – 1.02 (from ~3.4 at init) |
| checkpointing | every 45 steps, keep newest 2; 12/12 saves succeeded (11 checkpoints + final) |
Verified on all 457 steps: total == ce + 4·fd + 4·tc + 0.1·anchor (max deviation 9.4e-07). The KL
anchor was exactly 0.0 on every step — it is inactive under full-parameter training, so nothing
regularized this model toward the base distribution.
From rank-0 samples (one micro-batch per step of 16, so shares are estimates, not exact run-level values): the shaped terms fall from ~32 % of the objective over the first 50 steps to ~6 % over the last 50 (CE ~94 %, 4·fd ~4 %, 4·tc ~1 %) — the first-decision term is essentially solved during warmup.
Full-run statistics (all 16 ranks): loss minimum 0.690 @ step 199; block means 1–99 1.648 →
380–457 0.980. Pre-clip grad-norm peaked at 206,560 @ step 62, absorbed by max_grad_norm=1.0.
A shaped objective over assistant turns, combining:
Internal multi-turn tool-calling orchestration conversations (not released): 6,629 conversations, windowed to ≤44 k tokens → 7,310 training rows (3,441 conversations fit whole; 3,869 window-pieces from longer ones — conversations are split, never truncated) totalling 274.6 M tokens, of which 20.95 M (7.6 %) are supervised loss tokens across 41,466 assistant turns. Loss is masked to assistant turns only.
Standard transformers load. This is a multimodal (VL) architecture with a frozen vision tower;
all 1,188 tensors are included (832 language + 355 vision + 1 projection). lm_head is absent by
design — embeddings are tied.
python
from transformers import AutoModelForCausalLM, AutoProcessorm = AutoModelForCausalLM.from_pretrained("tzchen07/gemma4-31b-rovochat-full-sft-w1-260729",torch_dtype="bfloat16", device_map="auto", attn_implementation="sdpa")p = AutoProcessor.from_pretrained("tzchen07/gemma4-31b-rovochat-full-sft-w1-260729")
Note: processor_config.json is included. Trainer.save_model() does not write it, so
checkpoints saved that way fail to build the processor; it was copied from the base model.
Paired plain-CE control: gemma4-31b-rovochat-full-sft-w0-260801 — identical data, recipe, hardware and hyperparameters; no loss shaping (fd=tc=0, token_mean CE). Released so this model's shaped objective can be measured against a baseline rather than assumed. ⚠️ Loss values are not comparable across the two arms (different CE normalization), and the contrast is two-factor.
…-checkpoint-457
— same weights plus ZeRO-3 fp32 optimizer state, for resuming.
…-checkpoint-450
— step 450, likewise resumable.
Optimizer states are only usable to resume this run at the same world size (16) and DeepSpeed config; they are not portable to other topologies.