-
Hi friends,
I was trying to test the finetune/finetune.py script. It seems that state.best_model_checkpoint always return None leading to a failure at the end of the program. Is it that the program…
ttssp updated
9 months ago
-
StarCoderPlus uses StarCoder + RefinedWeb dataset for training but with a longer context length. Are there plans to release a version with a longer context length, such as 8192?
-
The reproduced pass@1 result of StarCoder on the MBPP dataset is 43.6*, which differs from the reported result of 52.7 in the paper. Can you explain that?
-
An obvious feature to me, but also not one that is simple to implement - is speculative sampling on the road map?
The idea would be using a second tiny-model combined with e.g. for greedy validatio…
-
Hi all, this issue will track the feature requests you've made to TensorRT-LLM & provide a place to see what TRT-LLM is currently working on.
Last update: `Jan 14th, 2024`
🚀 = in development
#…
-
**Describe the bug**
Can get work on tabby 0.13.1 or 0.14.0 follow by the quick-start guide, it's just start process with the a embed model
/opt/tabby/bin/llama-server -m /data/models/TabbyML/Nom…
-
Hi,
Thanks for sharing this work.
1) What's the best way to perform a quick analysis on a custom domain w/o fine tuning (zero shot or few shot)?
How should I prepare my input dataset and prompts…
-
It’s important to avoid ever using claims that are dependent on thousands of variables changing each day, such as, “With a context length of over 8,000 tokens, the StarCoder models can process more in…
-
# Environment
CPU architecture: x86_64
GPU name: NVIDIA A10
TensorRT branch: 9.0.0
TensorRT LLM: 0.1.3
Cuda: 12.1.66
Cudnn: 8.9.0
Container: registry.cn-hangzhou.aliyuncs.com/trt-hackathon/trt-…
-
In ablation study, you show multi round revision works better than single round revision. You also show wizardcoder outperforms Pretrained model starcoder. However, it is unknown how much wizardcoder …