kmn1024

neural_compressor/adaptor/ox_utils/quantizer.py dfs crash during "basic" tuning

1

When I use "basic" strategy tuning to quantize my model, I ran into this issue during one of the phases: ``` ... 2024-02-21 23:25:49 [INFO] Tune 73 result is: [Accuracy...

Reference for pretraining other small language models

1

The README mentions this codebase can act as a "reference for enthusiasts keen on pretraining language models under 5 billion parameters". I'm wondering if you could give a brief guide...

pymnn inference quality is unstable

6

# 平台(如果交叉编译请再附上交叉编译目标平台): # Platform(Include target platform as well if cross-compiling): Model converter compilation, model conversion, and pymnn compilation were all done on device (==Orange Pi 5 Pro, using CPU, which...

[Bug]: Model infers on Intel CPU, but crashes on ARM CPU (both systems using Ubuntu 22.04)

6

### OpenVINO Version 2024.1.0 ### Operating System Other (Please specify in description) ### Device used for inference CPU ### Framework None ### Model used Custom (a version of Hifi-GAN) ###...

## ⚙️ Request New Models - Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/docs/transformers/en/model_doc/mamba https://huggingface.co/state-spaces https://github.com/state-spaces/mamba/ - Is this model architecture supported by MLC-LLM? No ## Additional context Mamba...

spacy dependencies failure

6

- Nuitka version, full Python version, flavor, OS, etc. as output by *this exact* command. 2.2.3 Commercial: 2.5.1 Python: 3.11.9 (main, Apr 19 2024, 16:39:34) [GCC 11.2.0] Flavor: Anaconda Python...

[Bug] max_single_sequence_length gets overridden?

2

## 🐛 Bug With mlc-ai/Llama-3.1-8B-Instruct-q4f16_1-MLC (which supports "context_window_size": 131072), I'm trying to input an extremely long prompt (basically an entire book, and one question about the book). Despite setting "max_num_sequence":...

加 stablelm-3b-4e1t

1

大佬，如果我写个PR来加 [stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t)，您会接受吗？🙇🏽