-
# AI Forum 2023 | Future of Foundation Models
Link: https://www.youtube.com/watch?v=f6m0MpbNicU&list=WL&index=15&t=9s&ab_channel=MicrosoftResearch
This presentation starts by raising questions a…
-
Adding some of the newer SSM based mechanisms would be of interest, and the following dérivation would facilitate implementation.
https://srush.github.io/annotated-mamba/hard.html
-
Problem: The model generates repetitive, nonsensical outputs like "Breis" regardless of the input provided. This happens even with different generation settings (e.g., temperature, top_k, top_p).
fro…
-
I am on Windows 10. When I run
python setup_env.py -md models/Llama3-8B-1.58-100B-tokens -q i2_s
I get
ERROR:root:Error occurred while running command: Command '['cmake', '--build', 'build', '--conf…
-
`(.venv) PS C:\Users\jesse\Documents\source\BitNet> python setup_env.py --hf-repo HF1BitLLM/Llama3-8B-1.58-100B-tokens -q
i2_s`
```
Traceback (most recent call last):
File "C:\Users\jesse\Document…
-
I'm new to this specific project, and I don't say any of the following with high confidence.
Things that I see as important for quantization:
*Inference speed*
- AWQ seems best on this front, t…
-
https://github.com/microsoft/BitNet?tab=readme-ov-file
Can ollama switch to that to save more power.
-
I am trying to run below command on Ubuntu system following documentation.
**python setup_env.py --hf-repo HF1BitLLM/Llama3-8B-1.58-100B-tokens -q i2_s**
which is throwing below error while execution…
-
```bash
Traceback (most recent call last):
File "/home/deadbytes/Documents/BitNet/setup_env.py", line 202, in
main()
File "/home/deadbytes/Documents/BitNet/setup_env.py", line 180, in main
…
-
### Feature request
Is there any chance we coukd get this 4bit adam optimizer added to tranformers?
It has nearly the same performance as 32bit adam with significant drop in vram overhead.
[repo…