I-DLM-8B-N4-full-autobalance
I-DLM-8B — Full Model
| Property | Value |
|---|---|
| N (generation block size) | 4 |
| Training block_size | 3 |
| Type | Full Model |
| Auto-balance | Yes |
| Architecture | SDARForCausalLM (Qwen3-8B based) |
Install
pip install "sglang @ git+https://github.com/yjian-dev/sglang.git@jyq/idlm-release#subdirectory=python"
- Downloads last month
- 308
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support