Text Generation
Transformers
Safetensors
English
mistral
mteb
Eval Results (legacy)
text-generation-inference
Instructions to use BeastyZ/e5-R-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BeastyZ/e5-R-mistral-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BeastyZ/e5-R-mistral-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BeastyZ/e5-R-mistral-7b") model = AutoModelForCausalLM.from_pretrained("BeastyZ/e5-R-mistral-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BeastyZ/e5-R-mistral-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BeastyZ/e5-R-mistral-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BeastyZ/e5-R-mistral-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BeastyZ/e5-R-mistral-7b
- SGLang
How to use BeastyZ/e5-R-mistral-7b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "BeastyZ/e5-R-mistral-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BeastyZ/e5-R-mistral-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "BeastyZ/e5-R-mistral-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BeastyZ/e5-R-mistral-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BeastyZ/e5-R-mistral-7b with Docker Model Runner:
docker model run hf.co/BeastyZ/e5-R-mistral-7b
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,10 +2,9 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
datasets:
|
| 5 |
-
- BeastyZ/
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
-
|
| 9 |
model-index:
|
| 10 |
- name: e5-R-mistral-7b
|
| 11 |
results:
|
|
@@ -120,7 +119,7 @@ model-index:
|
|
| 120 |
- type: ndcg_at_1000
|
| 121 |
value: 61.149
|
| 122 |
- type: ndcg_at_3
|
| 123 |
-
value: 49
|
| 124 |
- type: ndcg_at_5
|
| 125 |
value: 51.141000000000005
|
| 126 |
- type: precision_at_1
|
|
@@ -1702,9 +1701,9 @@ model-index:
|
|
| 1702 |
- type: recall_at_10
|
| 1703 |
value: 89.517
|
| 1704 |
- type: recall_at_100
|
| 1705 |
-
value: 97
|
| 1706 |
- type: recall_at_1000
|
| 1707 |
-
value: 100
|
| 1708 |
- type: recall_at_3
|
| 1709 |
value: 79.72200000000001
|
| 1710 |
- type: recall_at_5
|
|
@@ -1733,19 +1732,19 @@ model-index:
|
|
| 1733 |
- type: map_at_5
|
| 1734 |
value: 1.199
|
| 1735 |
- type: mrr_at_1
|
| 1736 |
-
value: 94
|
| 1737 |
- type: mrr_at_10
|
| 1738 |
-
value: 97
|
| 1739 |
- type: mrr_at_100
|
| 1740 |
-
value: 97
|
| 1741 |
- type: mrr_at_1000
|
| 1742 |
-
value: 97
|
| 1743 |
- type: mrr_at_3
|
| 1744 |
-
value: 97
|
| 1745 |
- type: mrr_at_5
|
| 1746 |
-
value: 97
|
| 1747 |
- type: ndcg_at_1
|
| 1748 |
-
value: 92
|
| 1749 |
- type: ndcg_at_10
|
| 1750 |
value: 84.399
|
| 1751 |
- type: ndcg_at_100
|
|
@@ -1757,7 +1756,7 @@ model-index:
|
|
| 1757 |
- type: ndcg_at_5
|
| 1758 |
value: 88.52600000000001
|
| 1759 |
- type: precision_at_1
|
| 1760 |
-
value: 94
|
| 1761 |
- type: precision_at_10
|
| 1762 |
value: 86.8
|
| 1763 |
- type: precision_at_100
|
|
@@ -1871,6 +1870,4 @@ e5-R-mistral-7b is a LLM retriever fine-tuned from [mistralai/Mistral-7B-v0.1](h
|
|
| 1871 |
|
| 1872 |
- **Model type:** CausalLM
|
| 1873 |
- **Repository:** Welcome to our [GitHub](https://github.com/LeeSureman/ConRetriever) repository to obtain code
|
| 1874 |
-
- **Training dataset:** Dataset used for fine-tuning e5-R-mistral-7b is available [here](https://huggingface.co/datasets/BeastyZ/ConRetriever).
|
| 1875 |
-
|
| 1876 |
-
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
datasets:
|
| 5 |
+
- BeastyZ/E5-R
|
| 6 |
language:
|
| 7 |
- en
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: e5-R-mistral-7b
|
| 10 |
results:
|
|
|
|
| 119 |
- type: ndcg_at_1000
|
| 120 |
value: 61.149
|
| 121 |
- type: ndcg_at_3
|
| 122 |
+
value: 49
|
| 123 |
- type: ndcg_at_5
|
| 124 |
value: 51.141000000000005
|
| 125 |
- type: precision_at_1
|
|
|
|
| 1701 |
- type: recall_at_10
|
| 1702 |
value: 89.517
|
| 1703 |
- type: recall_at_100
|
| 1704 |
+
value: 97
|
| 1705 |
- type: recall_at_1000
|
| 1706 |
+
value: 100
|
| 1707 |
- type: recall_at_3
|
| 1708 |
value: 79.72200000000001
|
| 1709 |
- type: recall_at_5
|
|
|
|
| 1732 |
- type: map_at_5
|
| 1733 |
value: 1.199
|
| 1734 |
- type: mrr_at_1
|
| 1735 |
+
value: 94
|
| 1736 |
- type: mrr_at_10
|
| 1737 |
+
value: 97
|
| 1738 |
- type: mrr_at_100
|
| 1739 |
+
value: 97
|
| 1740 |
- type: mrr_at_1000
|
| 1741 |
+
value: 97
|
| 1742 |
- type: mrr_at_3
|
| 1743 |
+
value: 97
|
| 1744 |
- type: mrr_at_5
|
| 1745 |
+
value: 97
|
| 1746 |
- type: ndcg_at_1
|
| 1747 |
+
value: 92
|
| 1748 |
- type: ndcg_at_10
|
| 1749 |
value: 84.399
|
| 1750 |
- type: ndcg_at_100
|
|
|
|
| 1756 |
- type: ndcg_at_5
|
| 1757 |
value: 88.52600000000001
|
| 1758 |
- type: precision_at_1
|
| 1759 |
+
value: 94
|
| 1760 |
- type: precision_at_10
|
| 1761 |
value: 86.8
|
| 1762 |
- type: precision_at_100
|
|
|
|
| 1870 |
|
| 1871 |
- **Model type:** CausalLM
|
| 1872 |
- **Repository:** Welcome to our [GitHub](https://github.com/LeeSureman/ConRetriever) repository to obtain code
|
| 1873 |
+
- **Training dataset:** Dataset used for fine-tuning e5-R-mistral-7b is available [here](https://huggingface.co/datasets/BeastyZ/ConRetriever).
|
|
|
|
|
|