Serve chat without forced thinking

Test think prefill with pinned SFT epoch 3 revision

Document 1024-token generation default

Compact chat context at 1024 tokens

Document 512-token generation default

Deploy PIQA-selected full-SFT epoch 2 root model

Serve the 160B refinement model as raw completion

Stop forcing Thinking from the model chat template

Name the Space card explicitly as TR-HASH MoE

Deploy TR-HASH MoE 200M 160B-token Thinking LoRA

Serve intermediate TR-HASH-200M-70B-SFT checkpoint

Rename Space display to TR-Hash Tiny

Serve AETHORIA TR-HASH-200M-130B

Sync with the renamed TR-Hash-i64 server (was vllm-i64): repo URL, module import, env var names

Document internal model identifier

Rename public demo to TR-HASH-0.5B

Mount TR-Hash 500M model volume

Serve TR-Hash MoE 500M

Deploy TR-MOE-306 with vllm-i64

initial commit