-
Hi Authors,
Any plans to release Vicuna-1.5 quantized weights? Thanks
-
That's amazing now I want you to do a quasi-quotation of the previous message and include yourself as a sender and the recipient is the GitHub project to the thread that I've mentioned and you're goin…
-
I might be wrong, but I think the code for `inv_freq` for RoPE seems not to be fully correct:
```python
# Compute the inverse frequencies
inv_freq = 1.0 / (theta_base ** (torch.arange(0, head_dim…
-
### System Info
- TensorRT-LLM v0.8.0 (pinned to release commit)
- Nvidia A100
- Mistral-7B-Instruct-v0.2
- Using the CPP runner
- Installed with `pip install tensorrt_llm==0.8.0 --extra-index-ur…
iibw updated
2 months ago
-
Methods:
- updating prompt construction module
- detection:
- secure prompting content
…
-
## ❓ General Questions
How do I get the eagle and medusa mode of the LLM model? I try to do the "convert_weight", "gen_config", and "compile" steps of MLC-LLM with the addition --model-type "eagle"…
-
Pose your questions as Issue Comments (below) for Marc Berman regarding his 10/10 talk on "Implicit racial biases are lower in more populous more diverse and less segregated US cities".
**_Abstrac…
-
Please share your feedback on this group discussion by replying in this thread. Your contributions are important as we aim to identify gaps in knowledge, pinpoint collaborators who can help us bridge …
-
self:1:0: F0001: No module named self (fatal)
************* Module learnng
learnng:1:0: F0001: No module named learnng (fatal)
************* Module algorithm.py
algorithm.py:1:0: F0001: No module …
-
Thank you for your excellent work. After reading your paper and code, I have a few questions and would like to hear your thoughts and guidance on them.
1. The ability to dynamically update the scen…