-
see tinyllama pretraining script in lit-gpt, pytorch-labs repo from torch talk
-
RT
env:
```
root@0dea5388ce98:/workspace/InfiniLM# nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Wed_Apr_17_19:19:55_PDT_2024
Cuda compilatio…
-
### OpenVINO Version
2023.3
### Operating System
Fedora Silverblue 39
### Device used for inference
GPU
### Framework
PyTorch
### Model used
llava-hf/llava-1.5-7b-hf
### …
-
I want to run the tinyllama model and I wonder if there a way to run GGUF models with this crate. It seem much more common that models are using the GGUF format over the GGML format for models and con…
-
As far as I know, one can pretrain fine using TinyStories:
```python
litgpt/pretrain.py --data litgpt.data.TinyStories
```
Should we add this to the documentation?
Right now, we only have …
rasbt updated
7 months ago
-
In my opinion, the generation should be the same when draft model and target model is the same and temparature is 0.
But in this case, the output logits of draft model and target model have a bit d…
-
[TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0). This is my custom dataset: [BibleGPT-LORA](https://huggingface.co/datasets/oliverbob/biblegpt). Its a s…
-
curious how it performs on smaller models
-
This is a feature request to deploy Small Language Models (SLM) (3b or 1b). SLMs are improving quickly and are becoming good choice for narrowed scope usecases.
Examples can be TinyLlama, Minichat…
-
### OpenVINO Version
2024.3.0 https://github.com/rahulchaphalkar/openvino/tree/add-extension
### Operating System
Ubuntu 20.04 (LTS)
### Device used for inference
CPU
### Framework
None
### Mo…