-
执行了pip install -r requirements.txt
将所有模型都本地化了
执行python testing.py 报错
(whisperx-offline) jzxt@jzxt-SY-KL-H5…
-
Embedding dimension here is fixed to 1536 which is wrong as different embedding models might have different dimens
https://github.com/BerriAI/litellm/blob/fc5b75d1710ea1ea815746090fb154fc0f7717d8/l…
-
BAAI/bge-m3 과 nlpai-lab/KoE5 를 PR 로 추가하셨는데 제가 평가 해봤을때는 점수가 다르게 나옵니다. AutoRAG에서 직접평가하신 gte-multilingual-base도 평가해봤습니다만 그것은 소수점까지 모두 일치합니다. BAAI/bge-m3 과 nlpai-lab/KoE5 모델을 재평가해보심이 어떨까요..
평가 코드는 아래와 같이…
-
# OPEA Inference Microservices Integration for LangChain
This RFC proposes the integration of OPEA inference microservices (from GenAIComps) into LangChain [extensible to other frameworks], enabli…
-
### System Info
System Info:
AWS EC2 G4dn
Amazon Linux
Model:jinaai/jina-reranker-v1-tiny-en or jinaai/jina-reranker-v1-turbo-en
Hardware: Nvidia-smi
Using latest docker version
C…
-
Getting transformed features...
Calculating distances...
Maximum distance from cluster centers is 1.31
initial embedding size : (137984, 1536)
final embedding size : (13798, 1536)
0%| …
-
**Describe the bug**
When I run the example from examples/python/awq-quantized-model.md, but switching out phi-3 for llama-3.2-3b, I get an error message stating that `AttributeError: 'NoneType' objec…
-
I enjoy using this library very much. However, I notice that other embedding techniques like DINOv2 may also be used in building the search index, and perhaps leads to higher retrieval accuracy. Is th…
-
-
Hello,
I finally managed to use a local embedding model (mxbai-embed-large-v1) using new SentenceTransformerEmbeddingModel class (thenks to developper team for this work !!! ;-)).
```
sparse_em…