fjmgAI commited on
Commit
d332001
·
verified ·
1 Parent(s): dd8cb40

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -30,11 +30,12 @@ model-index:
30
  - type: accuracy
31
  value: 0.973160982131958
32
  name: Accuracy
 
33
  ---
34
  [<img src="https://cdn-avatars.huggingface.co/v1/production/uploads/67b2f4e49edebc815a3a4739/R1g957j1aBbx8lhZbWmxw.jpeg" width="200"/>](https://huggingface.co/fjmgAI)
35
  ## Fine-Tuned Model
36
 
37
- **`fjmgAI/reason-colbert-210M-EuroBERT`**
38
 
39
  ## Base Model
40
  **`EuroBERT/EuroBERT-210m`**
@@ -76,7 +77,7 @@ from pylate import indexes, models, retrieve
76
 
77
  # Step 1: Load the ColBERT model and Move the model to GPU if available, otherwise use CPU
78
  model = models.ColBERT(
79
- model_name_or_path=("fjmgAI/reason-colbert-210M-EuroBERT", trust_remote_code=True)
80
  )
81
 
82
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -165,7 +166,7 @@ documents_ids = [
165
  ]
166
 
167
  model = models.ColBERT(
168
- model_name_or_path=("fjmgAI/reason-colbert-210M-EuroBERT", trust_remote_code=True),
169
  )
170
 
171
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -210,4 +211,4 @@ This tuned model is designed to be used in scenarios that require **efficient em
210
  - **License:**
211
  Unfortunately, since the [ReasonIR data](https://huggingface.co/datasets/reasonir/reasonir-data) has been released under a cc-by-nc-4.0 license, we cannot release this model under an Apache 2.0 license. However, the authors of ReasonIR [released code to generate the data](https://github.com/facebookresearch/ReasonIR/tree/main/synthetic_data_generation). Anyone willing to reproduce the data could then easily reproduce this model under an Apache 2.0
212
 
213
- [<img src="https://github.com/lightonai/pylate/blob/main/docs/img/logo.png?raw=true" width="200"/>](https://github.com/lightonai/pylate)
 
30
  - type: accuracy
31
  value: 0.973160982131958
32
  name: Accuracy
33
+ license: cc-by-4.0
34
  ---
35
  [<img src="https://cdn-avatars.huggingface.co/v1/production/uploads/67b2f4e49edebc815a3a4739/R1g957j1aBbx8lhZbWmxw.jpeg" width="200"/>](https://huggingface.co/fjmgAI)
36
  ## Fine-Tuned Model
37
 
38
+ **`fjmgAI/reason-colBERT-210M-EuroBERT`**
39
 
40
  ## Base Model
41
  **`EuroBERT/EuroBERT-210m`**
 
77
 
78
  # Step 1: Load the ColBERT model and Move the model to GPU if available, otherwise use CPU
79
  model = models.ColBERT(
80
+ model_name_or_path=("fjmgAI/reason-colBERT-210M-EuroBERT", trust_remote_code=True)
81
  )
82
 
83
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
166
  ]
167
 
168
  model = models.ColBERT(
169
+ model_name_or_path=("fjmgAI/reason-colBERT-210M-EuroBERT", trust_remote_code=True),
170
  )
171
 
172
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
211
  - **License:**
212
  Unfortunately, since the [ReasonIR data](https://huggingface.co/datasets/reasonir/reasonir-data) has been released under a cc-by-nc-4.0 license, we cannot release this model under an Apache 2.0 license. However, the authors of ReasonIR [released code to generate the data](https://github.com/facebookresearch/ReasonIR/tree/main/synthetic_data_generation). Anyone willing to reproduce the data could then easily reproduce this model under an Apache 2.0
213
 
214
+ [<img src="https://github.com/lightonai/pylate/blob/main/docs/img/logo.png?raw=true" width="200"/>](https://github.com/lightonai/pylate)