-
I have tried the meta-llama/Llama-3-8b-chat-hf chatmodel and togethercomputer/m2-bert-80M-8k-retrieval embedding model with embeddingDimension: 768, but I'm having the following error many times when …
-
Based on timing reported in log files from running multiple scenarios in the H-GAC models, a few of the modules appear to have undesirable algorithmic properties (in particular, with runtimes suggesti…
-
While using Llama 3 models, sometimes, intermittently, I do not get model responses. As an example, I ran the following code in a loop 10 times:
```
import boto3
from langchain_aws.llms.bedrock imp…
-
I found if I just run the scripts to test "VisualWebArena benchmark" experiment. The task finnally will fail …
-
Hi, thank you for your incredible work. Now I want to conduct further research on the TUL problem.
I tried to process the model on the Geolife-all dataset with the following command line:
`python ma…
-
## Why this issue?
In f2f discussion, we talked about the difficulty in having a generative model for _both_ weekly hospitalisation _and_ bi-weekly variant frequencies _simultaneously_. There are a…
-
# Serial: 8s
```julia
using YAXArrays, Statistics, Zarr
using DimensionalData
using Dates
axlist = (
Dim{:time}(Date("2022-01-01"):Day(1):Date("2022-12-31")),
Dim{:lon}(range(1, 10, len…
-
Just an FYI, if it helps anyone else using the API in Simons or more recent:
when you do a /99/Models.bin request with the model_id and the directory, you actually have to pass the model_id twice, …
-
**Describe the bug**
The computation of bounds of the auxiliary variable is not accurate for `mul` or `pow` expressions.
It raises an exception because it does not take into account the right mem…
-
### What happened?
It seems llama-cli version 3952 doesn't generate any text response when the "--log-disable" parameter is set.
llama-cli version 3541 returns a text response regardless of the t…