jgalego commited on
Commit
9e5a633
·
verified ·
1 Parent(s): 6e3660f

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -18,6 +18,9 @@ A RISC-V computer (RV32IM + Zba) compiled into the layers of a stock `OlmoHybrid
18
 
19
  This is the standalone half of [Olmputer](https://huggingface.co/jgalego/olmputer), which puts the same layers in front of [allenai/Olmo-Hybrid-Instruct-DPO-7B](https://huggingface.co/allenai/Olmo-Hybrid-Instruct-DPO-7B) so that OLMo's `calc` tool calls run on the CPU inside its weights. It ports [Qwenputer](https://github.com/divagr18/qwenputer), which does this with Qwen3.5-4B, to OLMo-Hybrid's head shapes. The compiler is the `chipformer` package of [JGalego/olmputer](https://github.com/JGalego/olmputer).
20
 
 
 
 
21
  ## The machine
22
 
23
  | | |
 
18
 
19
  This is the standalone half of [Olmputer](https://huggingface.co/jgalego/olmputer), which puts the same layers in front of [allenai/Olmo-Hybrid-Instruct-DPO-7B](https://huggingface.co/allenai/Olmo-Hybrid-Instruct-DPO-7B) so that OLMo's `calc` tool calls run on the CPU inside its weights. It ports [Qwenputer](https://github.com/divagr18/qwenputer), which does this with Qwen3.5-4B, to OLMo-Hybrid's head shapes. The compiler is the `chipformer` package of [JGalego/olmputer](https://github.com/JGalego/olmputer).
20
 
21
+ > [!NOTE]
22
+ > Uses the architecture and head shapes of Ai2's [OLMo-Hybrid](https://huggingface.co/allenai/Olmo-Hybrid-Instruct-DPO-7B), none of its weights; not affiliated with or endorsed by Ai2.
23
+
24
  ## The machine
25
 
26
  | | |