-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
- [X] 3. Please note that if the bug-related issue y…
-
For different models, there are different token limitations.
For token user input should be less than half of the max token.
Refer `tokenUtils.js`
For nextjs it seems there are some features al…
-
Often you want to look at vectors over the vocabulary (eg the logits at a specific position). This is >50,000 dimensions and this is hard to interpret! I want there to be nice utils to visualize a vec…
-
OS Ubuntu 22.04
python 3.9.19
transformers 4.39.0
intel-extension-for-pytorch 2.1.20+git0e2bee2
torch 2.1.0.post0+cxx11.abi
torchvision 0.16.0+fbb4cc5
…
-
### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a…
-
### Describe the bug
~~When I enabled `WANDB_WATCH=all` in my Pytorch/Transformers training loop~~ (Seems to be unrelated to watch) I got a Recursion Limit Exception `maximum recursion depth exce…
-
长上下文模型Orion-14B-LongChat部署后成功后,最大token还是4096怎么解决?
-
Looking through Llama3 changes, I see that "ignore_merges" was added as a property to support conversion from tiktoken models. Can a native HF tokenizer be trained using this property? It's not clear…
-
### Your current environment
_environment not relevant here_
### 🐛 Describe the bug
VLLM has a [strict requirement on using `tiktoken==0.6.0`](https://github.com/vllm-project/vllm/blob/33e0823de583…
-
### Privileged issue
- [X] I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here.
### Issue Content
### Checked other resources
- [X] I added a ver…