mradermacher

/

model_requests

like 187

It's queued! :D

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#GigaChat3-10B-A1.8B-bf16-GGUF for quants to appear.

This model unfortunately failed our dryrun testing making any quants useless:

llama_model_load: error loading model: error loading model hyperparameters: key not found in model: deepseek2.attention.q_lora_rank
llama_model_load_from_file_impl: failed to load model

I also tried ai-sage/GigaChat3-10B-A1.8B but it had the same issue:

llama_model_load: error loading model: error loading model hyperparameters: key not found in model: deepseek2.attention.q_lora_rank
llama_model_load_from_file_impl: failed to load model

Damn, that's sad. Was really hoping to try out that model. Thank you for attempting it though!

There is hope. https://github.com/ggml-org/llama.cpp/pull/17420 got merged which probably fixes the issues we encountered.