-
Hi, thanks for the work!
I have a question regarding the calculation of alpha and beta coefficients (wscale and wbias in terms of code).
In the article, their application and calculations are p…
-
I am trying to quantize and export to tensorrt engine a llama 3 finetuned [model ](https://huggingface.co/damerajee/Gaja-v1.00). But I am able to quantize the model but however I am unable to export t…
-
### 起始日期 | Start Date
9/3/2024
### 实现PR | Implementation PR
_No response_
### 相关Issues | Reference Issues
_No response_
### 摘要 | Summary
When using vLLM to optimally utilize GPU space for faste…
-
### Question
I plotted my evaluated data with the interact_pareto_frontier() method and did not use the posterior mean model. Is there a simple way to set the evaluated values that do not belong to…
-
Hi there,
If I want to train a new ESRGAN model, a 2.5x upsampling/downsampling factor, for example, how do I get the corresponding pre-trained PSNR model?
-
**Describe the Issue**
As of 1.71.1 and the addition of rope_factors, newly created GGUFs (Llama3) seem to incur an inference speed hit on specifically Windows ~~and not Linux as far as I can tell.~~…
-
- #1159 enabled coloring by pLDDT values if B-factors are defined
- this means that the pLDDT options shows up for all archive entries
What do you think about adding a check and suppressing the pL…
-
`DefaultUtilityOptimizer.useCapacity()` is invoked in each timeslot to compute consumption. For `INDIVIDUAL` models like Frosty Storage that include multiple individuals, capacity is computed per-subs…
-
from mamba_ssm import Mamba2
model = Mamba(
# This module uses roughly 3 * expand * d_model^2 parameters
d_model=64, # Model dimension d_model
d_state=64, # SSM state expansion factor…
-
### Is there an existing plan for this?
- [X] I have searched the existing discussions, release notes, and documentation.
### Description of the Feature, Filter, or Functionality?
Hello,
Could w…