---
license: mit
base_model: zai-org/GLM-4.7-Flash
library_name: peft
pipeline_tag: text-generation
datasets:
  - TokenBender/glm47-pie-cpp-posttraining-data
tags:
  - glm
  - lora
  - grpo
  - reinforcement-learning
  - code
  - code-optimization
  - h100
---

# GLM-4.7-Flash PIE C++ GRPO LoRA

LoRA rank-16 GRPO adapter for
[`zai-org/GLM-4.7-Flash`](https://huggingface.co/zai-org/GLM-4.7-Flash),
trained with executable C++ correctness and performance rewards.

## Verified H100 Run

| Setting | Value |
| --- | --- |
| Accelerators | 8x NVIDIA H100 |
| Parallelism | TP4 / PP1 / EP8 |
| Sequence length | 4,096 |
| Rollout batch | 32 prompts x 8 samples |
| Global batch size | 256 |
| LoRA rank / alpha | 16 / 32 |
| Peak allocated memory | 75,957 MiB per GPU |
| Wall time | 653 seconds |

The validation run completed successfully, logged 256 rollout samples and 125
evaluation samples, and produced a synchronized parameter update across all
eight ranks. The before/after parameter hashes differ, all 16 synchronization
records agree across ranks, and timing evidence is marked verified.

## Files

- `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, checkpoint manifest, VRAM trace, and
  compact evidence summary.
- `evidence/sync_forensics/`: rank-by-rank parameter synchronization records.
- `evidence/rollout_dumps/`: the training and evaluation rollout tensors.

## Loading

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained(
    "zai-org/GLM-4.7-Flash",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(
    base,
    "TokenBender/glm47-flash-pie-cpp-lora-r16-grpo-h100",
)
```

Training code:
[TokenBender/browser-is-all-you-need](https://github.com/tokenbender/browser-is-all-you-need/tree/client/glm47-h100-posttraining)