Downloads · 30 days
93
2% of all-time downloads
sweep-next-edit-v2-7B-AWQ
henrik3/sweep-next-edit-v2-7B-AWQ
sweep-next-edit-v2-7B-AWQ is a text generation model from henrik3. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Converted via llm compressor, with 200 examples from henrik3/sweep-calibration for calibration (which is to be fair not best quality but should be fine)
All-time downloads
6.1K
Public
Parameters
2B
15.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.5 GB · 100%
Parameter types
How the weights are stored.
I326.5B · 85%
Try a prompt
Base models
Model card
From the Hugging Face model README
Converted via llm compressor, with 200 examples from henrik3/sweep-calibration for calibration (which is to be fair not best quality but should be fine)
Performance
Sglang & RTX 2000 Ada (224GB/s bandwidth)
Command:
python3 -m sglang.launch_server --model-path henrik3/sweep-next-edit-v2-7B-AWQ --port 8000 --host 0.0.0.0 --trust-remote-code --mem-fraction-static 0.8 --context-length 16384 --speculative-algorithm NGRAM --speculative-num-draft-tokens 4
Stats
- ~6900 input tokens
- ~250 output tokens
- ~600ms response time
Find the original model here: https://huggingface.co/sweepai/sweep-next-edit-v2-7B
- Task
- Text Generation
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Apr 3, 2026
- Updated
- Apr 14, 2026