Downloads · 30 days
10
27% of all-time downloads
glm47-flash-pie-cpp-lora-r16-sft-h100
TokenBender/glm47-flash-pie-cpp-lora-r16-sft-h100
glm47-flash-pie-cpp-lora-r16-sft-h100 is a text generation model from TokenBender. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as mit.
LoRA rank-16 supervised fine-tuning adapter for zai-org/GLM-4.7-Flash, trained on the PIE C++ performance task.
All-time downloads
37
Public
Repo size
767 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin486 MB · 63%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026
- SHA
- f1ac8df3
Try a prompt
Base models
Model card
From the Hugging Face model README
GLM-4.7-Flash PIE C++ SFT LoRA
LoRA rank-16 supervised fine-tuning adapter for
zai-org/GLM-4.7-Flash,
trained on the PIE C++ performance task.
Result
The full 1,259-task evaluation produced:
| 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% |
The complete per-task records and generated responses are under
evidence/eval/.
Training Profile
| 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 |
Files
adapter_model.binandadapter_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.
Loading
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-sft-h100",
)
Training code: TokenBender/browser-is-all-you-need
- Task
- Text Generation
- Library
- peft
- License
- mit
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026