motexture's cData models
#654
by
SuperNintendoChalmers
- opened
This model author has a dataset of low-level coding like C/C++ and finetunes existing small models on that dataset. This is interesting to me. Two models are:
- https://huggingface.co/motexture/Cwen-7B-Instruct
- https://huggingface.co/motexture/LlamaXCoder-3.2-3B-Instruct
You've already done their SmolLM2-based models called SmolLCoder, thank you.
It's queued! :D
I love low level C/C++
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#Cwen-7B-Instruct-GGUF and https://hf.tst.eu/model#LlamaXCoder-3.2-3B-Instruct-GGUF for quants to appear.
mradermacher
changed discussion status to
closed
Cwen failed: examples/imatrix/imatrix.cpp:437: GGML_ASSERT(!llama_vocab_get_add_eos(vocab)) failed
Many thanks, looking forward to playing with the one that worked.