Qwen3-1.7B compression L+4096 final
Standard BF16 Hugging Face model, exported from training step 100. Weights, configuration, tokenizer, and the thinking chat template are at the repository root.
Source checkpoint: hi-todayis-jh/per-context-rb-l0-4096-no-eos-qwen3-1.7b-compression-bs32-32k-146102-step_100 at commit 1f3abb5e21eceb79c01684d43cc4e8485993fab0.
Load this repository directly with AutoModelForCausalLM.from_pretrained or vLLM. Use enable_thinking=True in the tokenizer chat template for the existing thinking evaluations.
The export manifest records source provenance, file checksums, tensor validation, and a successful Transformers CPU load and forward pass.