https://huggingface.co/Sadatsami/Kimi-K3-0.40B
Model Name: Sadatsami/Kimi-K3-0.40B
Model URL: https://huggingface.co/Sadatsami/Kimi-K3-0.40B
This is a tiny version of moonshotai/Kimi-K3 created for testing and development.
Result of trying to use GGUF My Repo to auto-generate quants (https://huggingface.co/spaces/ggml-org/gguf-my-repo):
"Error converting to fp16: INFO:hf-to-gguf:Loading model: Kimi-K3-0.40B
WARNING:hf-to-gguf:Failed to load model config from downloads/tmp373oa_s6/Kimi-K3-0.40B: The repository downloads/tmp373oa_s6/Kimi-K3-0.40B contains custom code which must be executed to correctly load the model. You can inspect the repository content at /home/user/app/downloads/tmp373oa_s6/Kimi-K3-0.40B .
You can inspect the repository content at https://hf.co/downloads/tmp373oa_s6/Kimi-K3-0.40B.
Please pass the argument trust_remote_code=True to allow custom code to be run.
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: KimiK3ForConditionalGeneration
ERROR:hf-to-gguf:Model KimiK3ForConditionalGeneration is not supported"
uh, let's try but it might fail with same error for us as well, but let's see, not sure when the official repo was updated =)
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#Kimi-K3-0.40B-GGUF for quants to appear.