metadata
base_model: harheem/bge-m3-nvidia-ko-v1
language:
- en
library_name: sentence-transformers
license: apache-2.0
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dataset_size:1K<n<10K
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
- llama-cpp
- gguf-my-repo
widget:
- source_sentence: 하이브리다이저란 무엇인가요?
sentences:
- 하이퍼바이저는 보안에서 어떤 역할을 합니까?
- 지난 몇 년간 CUDA 생태계는 어떻게 발전해 왔나요?
- 로컬 메모리 액세스 성능을 결정하는 요소는 무엇입니까?
- source_sentence: 임시 구독의 용도는 무엇입니까?
sentences:
- 메모리 액세스 최적화에서 프리패치의 역할은 무엇입니까?
- CUDA 인식 MPI는 확장 측면에서 어떻게 작동합니까?
- CUDA 8이 해결하는 계산상의 과제에는 어떤 것이 있습니까?
- source_sentence: '''saxpy''는 무엇을 뜻하나요?'
sentences:
- CUDA C/C++의 맥락에서 SAXPY는 무엇입니까?
- Numba는 다른 GPU 가속 방법과 어떻게 다른가요?
- 장치 LTO는 CUDA 애플리케이션에 어떤 이점을 제공합니까?
- source_sentence: USD/Hydra란 무엇인가요?
sentences:
- 쿠다란 무엇인가요?
- y 미분 계산에 사용되는 접근 방식의 단점은 무엇입니까?
- Pascal 아키텍처는 통합 메모리를 어떻게 개선합니까?
- source_sentence: CUDAcast란 무엇인가요?
sentences:
- CUDACast 시리즈에서는 어떤 주제를 다룰 예정인가요?
- 이 게시물에 기여한 것으로 인정받은 사람은 누구입니까?
- WSL 2에서 NVML의 목적은 무엇입니까?
model-index:
- name: BGE base Financial Matryoshka
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.5443037974683544
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7749648382559775
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8523206751054853
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9409282700421941
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.5443037974683544
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2583216127519925
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.17046413502109703
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09409282700421939
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.5443037974683544
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7749648382559775
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8523206751054853
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9409282700421941
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7411108924386547
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.677065054807671
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6802131506478553
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.5386779184247539
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7749648382559775
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8593530239099859
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9451476793248945
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.5386779184247539
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2583216127519925
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.17187060478199717
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09451476793248943
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.5386779184247539
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7749648382559775
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8593530239099859
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9451476793248945
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7413571133247474
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.6759917844306029
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.678939165210132
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.540084388185654
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7791842475386779
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8621659634317862
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9423347398030942
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.540084388185654
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.25972808251289264
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1724331926863572
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09423347398030943
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.540084388185654
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7791842475386779
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8621659634317862
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9423347398030942
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7403981257690416
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.6756379344986938
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6787046866761269
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.5218002812939522
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7679324894514767
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8635724331926864
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9367088607594937
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.5218002812939522
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.2559774964838256
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.17271448663853725
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09367088607594935
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.5218002812939522
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7679324894514767
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8635724331926864
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9367088607594937
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7305864977688176
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.6641673922264634
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6671648971944116
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.509142053445851
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7426160337552743
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8284106891701828
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9310829817158931
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.509142053445851
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.24753867791842477
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.16568213783403654
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09310829817158929
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.509142053445851
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.7426160337552743
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.8284106891701828
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9310829817158931
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7135661304090457
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.6444829549259928
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6474431148702396
name: Cosine Map@100
hongkeon/bge-m3-nvidia-ko-v1-Q4_K_M-GGUF
This model was converted to GGUF format from harheem/bge-m3-nvidia-ko-v1 using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo hongkeon/bge-m3-nvidia-ko-v1-Q4_K_M-GGUF --hf-file bge-m3-nvidia-ko-v1-q4_k_m.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo hongkeon/bge-m3-nvidia-ko-v1-Q4_K_M-GGUF --hf-file bge-m3-nvidia-ko-v1-q4_k_m.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo hongkeon/bge-m3-nvidia-ko-v1-Q4_K_M-GGUF --hf-file bge-m3-nvidia-ko-v1-q4_k_m.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo hongkeon/bge-m3-nvidia-ko-v1-Q4_K_M-GGUF --hf-file bge-m3-nvidia-ko-v1-q4_k_m.gguf -c 2048