Downloads · 30 days
169
9% of all-time downloads
GLM-4.7-Flash-Derestricted
koute/GLM-4.7-Flash-Derestricted
GLM-4.7-Flash-Derestricted is a text generation model from koute. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
This is a GLM-4.7-Flash model which has been uncensored using the Norm-Preserving Biprojected Abliteration methodology, similar to other models from the 'derestricted' family.
All-time downloads
1.9K
Public
Parameters
31.2B
62.5 GB on disk
Likes
34
Public
Repo makeup
Click a slice to open those files.
.safetensors62.4 GB · 100%
Parameter types
How the weights are stored.
BF1631.2B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
GLM-4.7-Flash-Derestricted
This is a GLM-4.7-Flash model which has been uncensored using the Norm-Preserving Biprojected Abliteration methodology, similar to other models from the 'derestricted' family.
Benchmark results
All benchmarks were measured using a local vLLM instance and inspect_evals.
MMLU-Pro (subset of 200 samples picked at random)
- GLM-4.7-Flash: 0.715, 694606 output tokens
- GLM-4.7-Flash-Derestricted: 0.755, 632992 output tokens
Measured with:
LOCAL_API_KEY="dummy" LOCAL_BASE_URL="http://127.0.0.1:9001/v1" uv run inspect eval inspect_evals/mmlu_pro --model "openai-api/local/glm-4.7-flash-derestricted" --seed 123456 --reasoning-history all --log-dir eval-logs-glm-4.7-flash-derestricted-mmlu-pro --frequency-penalty 0 --presence-penalty 0 --temperature 0.7 --top-p 0.95 --max-tokens 8192 --max-connections 200 --sample-shuffle 6375934876 --limit 200
- Task
- Text Generation
- Library
- transformers
- Type
- glm4_moe_lite
- License
- mit
- Languages
- en, zh
- Created
- Jan 24, 2026
- Updated
- Jan 25, 2026