cerebras/DeepSeek-V3.2-REAP-508B-A37B

#1607
by Rubertigno - opened

gguff
thanks a lot

It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#DeepSeek-V3.2-REAP-508B-A37B-GGUF for quants to appear.

Sorry I forgot that DeepseekV32ForCausalLM is not yet supported by llama.cpp. Please follow https://github.com/ggml-org/llama.cpp/issues/16331 for DeepseekV32ForCausalLM support. Ideally remind me once it is supported as I will likely forget about this request by then. They already work on it for a quarter a year so don't expect any quick progress. I have to say createthis is super dedicated on implementing this super complicated architecture.

Sign up or log in to comment