-
email is multipart alternative plus image attachment
if the text part is removed then there is no issue with embed
(as reported by SysPete)
-
Langchaingo is using indirectly github.com/pkoukk/tiktoken-go v 0.1.6 while newer OpenAI embedding models (text-embedding-3-small, text-embedding-3-large) had been added in 0.1.7...
-
Why is the index of other models in the experiment much lower than that of the original paper ( such as CoLA ), because there are different abnormal embedding methods ( not seen in the text ) ?
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Is your feature request related to a problem? Please describe.
> Data-in Data-out is a code name, the official…
-
### Description
Some inference API providers now support embedding models with each dimension defined as a single bit. For example, the v3 models from Cohere offer this capability. Since we already h…
-
### System Info
peft==0.13.2
accelerate==1.0.1
torch==2.4.0
peft_config
```python
peft_config = PromptTuningConfig(
task_type=TaskType.CAUSAL_LM,
prompt_tuning_init=PromptTuningI…
-
Hello There,
This may not be specifically a bug, but there seems to be some issue.
For a single chat request sent from bot UI, metrics report that 3 or 3x Open AI requests were made. Also the toke…
-
Help the flutter plugin ecosystem by putting up pull requests to the top 10 still not migrated plugins. If a plugin only has references in example app code skip it (and add another from the list). If …
-
As illustrated [here](https://github.com/SciSharp/LLamaSharp/issues/178#issuecomment-1787672408), text completion and text embedding are important for many scenes. Currently LLamaSharp prefer to chat …
-
### Have you searched existing issues? 🔎
- [X] I have searched and found no existing issues
### Desribe the bug
I have built a model with partial_fit (using the code found in the documentation). …