Commit History
-
Card: correctness, thinking control, conversion notes and manifest for the recommended files
Verified signatureThanks for pulling the two CPU+GPU files into this repo and for the card update — this adds the details behind them, as asked in the Space thread. What the PR adds to the README, keeping your structure and the OpenBMB sections as they are: - **Correctness** — the 8-question gate on CPU and GPU (Mac, Galaxy S26 with full OpenCL delegation, iPhone 17 Pro), GSM8K n=100 with thinking off against the bf16 reference (92 / int8 91 / int4 86–87), and the thinking-mode caveat: int4's reasoning chains run ~4× longer than int8's and hit the budget; int8 is the file when the reasoning has to finish. - **Controlling thinking** — the model thinks by default; how `enable_thinking` reaches the template (ThinkingConfig / extra context / CLI flags), the output budget it needs, and the sampling OpenBMB recommends. - **Conversion notes** — what makes these files run on both backends: the checkpoint's `chat_template.jinja` embedded verbatim with the thought channel declared; the int4 zero-scale fix (13 a…f3e4664 -
Add performance data
LiVerified signature45a0e85 -
Update README.md (#2)
Li- Update README.md (07af107d525bdb8cc6b9058415d1cabd7f65213d)5af0fc9 -
Upload MiniCPM5-2B_int8.litertlm with huggingface_hub
Verified signature898fe54 -
Upload MiniCPM5-2B_int4.litertlm with huggingface_hub
Verified signature0953e6a
-
upload MiniCPM5-2B
Verified signatureb4fe2b3
-
Add model card
Verified signaturef78c959 -
initial commit
Verified signaturefef1dc8