-
Hi, do you have code for reproducing any of your experiments with federated finetuning of llama-7b (from the paper)?
Or maybe some of the existing examples can be adapted to do it?
-
Dear @dusty-nv ,
I'm trying the example code on web page: [Function Calling](https://dusty-nv.github.io/NanoLLM/chat.html#function-calling).
I tried both Llama-2-7b-chat-hf and Meta-Llama-3-8B-…
-
I have a finetuned llama 2 7B chat model which I am deploying to an endpoint using DJL container. After deploying when I tested the model, the model output quality has degraded (The output seems to be…
-
I have fine-tuned the Llama 3.1 8b model. I have added new tokens I am facing an issue while saving LoRA adapters and loading the model for inference. The error I get is,
> RuntimeError: Error(s) …
-
### System Info
I am getting the following error, but this error should not be there -
cannot import name 'ShardedDDPOption' from 'transformers.trainer'
I have the following versions installed - …
-
How can I deal with it?
Traceback (most recent call last):
File "/home/tangxinyu/anaconda3/envs/po/lib/python3.10/site-packages/retrying.py", line 251, in call
attempt = Attempt(fn(*args, *…
txy77 updated
1 month ago
-
## Description
As a developer of caikit NLP, I want to test Llama-7b models with prompt tuning and fine tuning techniques to evaluate for quality and performance.
## Discussion
a. We want to t…
-
Hello, we have merged the model "zhangyupeng/llava-7b-llama-2-7b-chat" by ourselves. Two 3090 Gpus are used for training, Batch_size=2 and grad_accumulation_steps=40. The following problems appear du…
-
Hi, thanks for your great work.
I am following the instructions to install and run the test scripts.
I tried two systems, one with 4xA100 40G, the other with 4xA100 80G.
I use the following…
-
Hi :) I have an issue with how to calculate the relevance scores w.r.t two (or more) output values for lxt.model.llama.
Initially, following your demo in llama, I write the following code.
```py…