-
### Feature request
Hi! I’ve been researching LLM quantization recently ([this paper](https://arxiv.org/abs/2405.14852)), and noticed a potentially improtant issue that arises when using LLMs with 1-…
-
**Describe the solution you'd like**
A new option in the admin settings to allow using embeddings based search among the chats. Allowing also to specify the embeddings engine to use (as they are not …
-
### Issue with current documentation:
I am using LLAMA-2 13 B model with langchain
For embeddings i am using
embeddings = HuggingFaceInstructEmbeddings(
model_name="WhereIsAI/UAE-Large-V…
-
Ever since the last 2+ versions, for what-ever reason, the loading of the plugin (and notes) is taking an incredibly long time. When I click on another note, I have to wait over a minute. During which…
-
## Checks for [pkgsimil (v0.1.2.043)](https://github.com/ropensci-review-tools/pkgsimil)
git hash: [040d4b8f](https://github.com/ropensci-review-tools/pkgsimil/tree/040d4b8f4faf2c74c76ce5e179bfb6899f…
-
Great crate!
I was able to speed up embeddings by making the following changes -
1. expose n_ubatch
2. setting n_ubatch and n_batch to 2048
3. initialize llamabatch with n-tokens with 2048
4…
srv1n updated
4 months ago
-
Hi, great project!
How hard would it be to extract embeddings from the LLMs?
-
I am trying to fine-tune a SentenceTransformer model on a retrieval dataset using a custom distance metric as the similarity function. My goal is to generate a token_embedding for the query and a sent…
-
Hi, does the code repo include the code for interpolation without finetuning E5
-
[ ] I checked the [documentation](https://docs.ragas.io/) and related resources and couldn't find an answer to my question.
**Your Question**
How to calculate total tokens consumption for evaluati…