# LLM architecture Dots1ForCausalLM conversion to GGUF

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-architecture-dots1forcausallm-conversion-to-gguf%2F158368%3E%5C
**Category:** Models\
**Created:** [June 7, 2025, 1:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-architecture-dots1forcausallm-conversion-to-gguf%2F158368 "2025-06-07T13:47:43Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![FBTMAML](https://avatars.discourse-cdn.com/v4/letter/f/958977/32.png) [@FBTMAML](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FFBTMAML)%5C
**Post date:** [June 7, 2025, 1:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-architecture-dots1forcausallm-conversion-to-gguf%2F158368%2F1 "2025-06-07T13:47:43Z")

</div>

rednote-hilab/dots.llm1.inst model cannot be converted to GGUF format  
llama.cpp/convert\_hf\_to\_gguf.py ./mymodels/dots.llm1.inst --outtype bf16 --outfile ./quantized\_models/dots.llm1.inst\_BF16.gguf  
INFO:hf-to-gguf:Loading model: dots.llm1.inst  
ERROR:hf-to-gguf:Model Dots1ForCausalLM is not supported

is there a way to get teh conversion done ?

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [June 7, 2025, 3:53pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-architecture-dots1forcausallm-conversion-to-gguf%2F158368%2F2 "2025-06-07T15:53:44Z")

</div>

Hmm… This?

> <https://github.com/ggml-org/llama.cpp/issues/5142>
>
> I use python convert-hf-to-gguf.py /fengpo/github/Yi-34B-Chat-8bits.
> I get this… error:
> 
> File "/fengpo/github/llama.cpp/convert-hf-to-gguf.py", line 1335, in main
> model\_instance = model\_class(dir\_model, ftype\_map\[args.outtype\], fname\_out, args.bigendian)
> File "/fengpo/github/llama.cpp/convert-hf-to-gguf.py", line 57, in \_\_init\_\_
> self.model\_arch = self.\_get\_model\_architecture()
> File "/fengpo/github/llama.cpp/convert-hf-to-gguf.py", line 254, in \_get\_model\_architecture
> raise NotImplementedError(f'Architecture "{arch}" not supported!')
> NotImplementedError: Architecture "LlamaForCausalLM" not supported!.
> 
> This also contain LlamaForCausalLM.
> !\[image\](https://github.com/ggerganov/llama.cpp/assets/12029452/f803d6bd-d671-45a4-bf41-0cc707d1b607)

> Galunid  
> `convert-hf-to-gguf.py` never supported llama based models. Please use `convert.py`.