-
-
Home-Assistant: 2024.8.1
llama-conversation: 0.3.6
webcolors: 1.13
Exact same issue was marked as fixed in 0.3.3 but appears not to be: https://github.com/acon96/home-llm/issues/165
What is …
-
I meet coredump when decoding with multi-thread. It cored in rust function `tokenizers_decode`,rust/src/lib.rs:199. here is the core backtrack.
why does it do not support multi-thread? I think dec…
-
### System Info
- `transformers` version: 4.42.0
- Platform: Linux-5.15.0-105-generic-x86_64-with-glibc2.35
- Python version: 3.9.19
- Huggingface_hub version: 0.23.4
- Safetensors version: 0.4…
-
Hi there,
Thank you for the great contributions!
There have been many new models released since the benchmark was published. Do you have any plans to include some of these recent models, such as…
-
### Proposal
I'm attempting to record an interaction with a gRPC server, I've setup the server with the required descriptor files, but I'm seeing a crash when running in record mode:
```
wiremock…
-
the snapshot is
I wonder is the tokenizer.model is not rigth? But I download it from https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/tree/main/original.
How can i fix this problem…
-
E:\ComfyUI\models\LLM\Meta-Llama-3.1-8B-bnb-4bit
Unused kwargs: ['_load_in_4bit', '_load_in_8bit', 'quant_method']. These kwargs are not used in .
transformers version 4.44 or 4.43, this warning m…
-
Hello,
Using the quantization config provided by torchtune, I am unable to run a quantization of llama-3-70b.
```shell
tune run quantize --config configs/custom_quantization_untrained_llama.y…
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
- [X] 3. Please note that if the bug-related issue y…