-
I am using the below code to pull the information, it was working fine yesterday but it is not returning any content in json's body.
Can you please help ?
```python
import json
from argparse i…
-
Prefacing that this isn't urgent. When using the recently added M1 GPU support, I see an odd behavior in system resource use. When using all threads -t 20, the first initialization follows the instruc…
-
I'm comparing the tokenization between original Meta repo and llama.cpp with LLaMA (also had same issue with LLaMA v2).
For example, tokenizing the prompt "Hello world" and " Hello world" gives the…
-
**Describe the bug**
Training fails due to "exits with return code = -7" without further explanations.
The is the full log:
```
root@5b7db410cd49:/app/dream_llm/casual_lm# deepspeed --num_gpus=4 r…
-
### System Info
System info:
- Code: Current `main` branch, installed via: `pip install git+https://github.com/huggingface/transformers` on 22nd March 2023
### Who can help?
@ArthurZucker @sgugg…
-
We need a large English natural language dataset approx 100B tokens which we can use as a mixture with the EuroPMC and other chemistry datasets.
Possible candidates
* Wikipedia
* Slices of The Pi…
-
Meta just released llama 2 model, allowing commercial usage
https://ai.meta.com/resources/models-and-libraries/llama/
I have checked the model implementation and it seems different from llama_v1…
-
This bug was originally filed in Launchpad as [LP: #1739023](https://bugs.launchpad.net/cloud-init/+bug/1739023)
Launchpad details
affected_projects = []
assignee = None
assignee_name = None
date_cl…
-
I am using Azure DevOps Release Pipeline to automate the process of rolling out CrowdStrike across our organization, I am currently running a POC and have provisioned 3 Azure VMs:- 2 Windows machines …
-
i used tiiuae/falcon-40b
and want to doing full fine-tuning by lima instruction dataset
`model = tp.tensor_parallel(model, sharded=True)`
just use like this and i have 1) A100 80GB * 2 and an…