Views
No views yet
zai-org/GLM-4.7-Flash,
trained on the PIE C++ performance task.| Metric | Result |
|---|---|
| Pass rate | 90.79% |
| Valid format rate | 97.70% |
| Correct and faster rate | 28.36% |
| Mean speedup when correct and faster | 1.43x |
| Mean reward | 0.8980 |
| Timeout rate | 0.00% |
evidence/eval/.| Setting | Value |
|---|---|
| Accelerators | 8x NVIDIA H100 |
| Parallelism | TP4 / PP1 / EP8 |
| Sequence length | 4,096 |
| Max tokens per GPU | 24,576 |
| Global batch size | 32 |
| LoRA rank / alpha | 16 / 32 |
| Peak allocated memory | 36,039 MiB per GPU |
| Checkpoint | Step 244 |
adapter_model.bin and adapter_config.json: loadable PEFT adapter.adapter_megatron_tp*_pp0.pt: four Megatron tensor-parallel shards.training_state_rank*.pt: per-rank training state.evidence/training/: run receipt and VRAM trace.evidence/eval/: complete evaluation summaries, records, and generations.1from peft import PeftModel
2from transformers import AutoModelForCausalLM
3
4base = AutoModelForCausalLM.from_pretrained(
5 "zai-org/GLM-4.7-Flash",
6 trust_remote_code=True,
7)
8model = PeftModel.from_pretrained(
9 base,
10 "TokenBender/glm47-flash-pie-cpp-lora-r16-sft-h100",
11)