-
During the use of LoRA fine-tuning, everything was normal, but the following issue arose during full-scale fine-tuning.
I use the following script for full fine-tuning :
```shell
#!/bin/bash
N…
-
Accelerate fails when launched on multi-gpu due to NCCL timeout.
`accelerate launch --multi_gpu --num_processes 2 --mixed_precision=bf16 --config_file conf/accelerate/accelerate_base.yaml exampl…
-
### System Info
I am finetuning Llama3-8b-Instruct model. Here is the Jupyter Notebook of the steps, i followed to perform the finetuning:
https://gitlab.com/keerti4p/llama3-8b-instruct-finetune/-…
-
**Command: tune run lora_finetune_single_device --config llama3_1/8B_lora_single_device**
**Output**:
```
INFO:torchtune.utils._logging:Running LoRAFinetuneRecipeSingleDevice with resolved config:…
-
### Proposal to improve performance
The spec dec performance of Eagleis worse than expected as shown below:
Model: [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llam…
-
I find Microsoft's Phi 3.5 vision instruct performs much better than Florence 2. Since it's an instruct model, it also has the benefit of taking text instruction as input to help describing the images…
-
Hi, Thanks for your wonderful work.
I am struggling using my lora tuned model.
I conducted following steps
1. finetuning with lora
- Undi95/Meta-Llama-3-8B-Instruct-hf model base
- llama3 …
-
## Summary
I am considering integrating sLM into the WelsonJS project. The leading candidate currently under review is Phi-3.5-mini.
If there are any updates on this matter, I will comment them in…
-
### Prerequisites
- [X] I have read the [documentation](https://hf.co/docs/autotrain).
- [X] I have checked other issues for similar problems.
### Backend
Local
### Interface Used
CLI
### CLI Co…
-
I want to lora finetune Qwen2.5-32B-Instruct-AWQ model(4bit quant already) through llama-factory, but occured an error.
`
[INFO|configuration_utils.py:677] 2024-11-21 19:44:25,957 >> loading confi…