-
text-embeddings-router start an embedding serving, but always got the error 【 Input validation error: inputs must have less than 512 tokens】,which param should i use to change max tokens of input?512 …
-
### What happened?
Hi there, I tried to upload two PDF files to a persistant collection and delete one of them. But I received Warning Messages: "Delete of nonexisting embedding ID". This Warning onl…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version:2.4-20240725-2822d872-amd64
- Deployment mode(standalone or cluster)…
-
### Describe your problem
def encode_queries(self, query: str):
emd, used_tokens = self.mdl.encode_queries(query)
if not TenantLLMService.increase_usage(
self.t…
-
### Bug Description
I got retrying error raised on running batch embeddings with AzuerOpenAI, and I wonder how do I make it wait for the limited time (60s per AOAI but 30s per raised error code) and …
-
I used the following code to sft llama3:
```
import os
import wandb
os.environ["WANDB_PROJECT"] = "unsloth-mimic-20240814" # name your W&B project
os.environ["WANDB_LOG_MODEL"] = "checkpoint" …
-
### System Info
It seems like executor API ignores `prompt_vocab_size` argument and passes `max_prompt_embedding_table_size` to trt engine instead.
I observe such behaviour using either 0.10.0 p…
-
The parser should support the shorthand operators, introduced with Oracle 23.4 (vector functionality). Currently, the code below leads to parse errors. As a workaround, the classical syntax can be use…
-
## Task Description
**Title:** Update `embedding_group` Table with `message_id` Column When Creating a Message Object
**Description:**
When a new object of type `message` is created, it should trigg…
-
### System Info / 系統信息
8卡A-800,cuda12.2,
transformers 4.40.2
torch 2.1.2
### Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?
- [ ] docker / docker
- [X] pip install / 通过 pip …