lbourdois commited on
Commit
be9af5b
·
verified ·
1 Parent(s): b622efa

Trimmed Danish 16384 tokens

Browse files
Files changed (2) hide show
  1. README.md +1 -2
  2. config.json +1 -1
README.md CHANGED
@@ -24,7 +24,6 @@ This trimmed model should perform similarly to the original model with only **16
24
  | **Vocabulary size** | 151,643 tokens | 16,384 tokens | **89.20%** |
25
  | **Model size** | 595,776,512 params | 457,244,672 params | **23.25%** |
26
 
27
- ![image](https://cdn-uploads.huggingface.co/production/uploads/613b0a62a14099d5afed7830/xyTFk3gLOL-4MQZSfKCgt.png)
28
 
29
  ## Mining Dataset Statistics
30
 
@@ -36,7 +35,7 @@ This trimmed model should perform similarly to the original model with only **16
36
  ```python
37
  from sentence_transformers import SentenceTransformer
38
  # Download from the 🤗 Hub
39
- model = SentenceTransformer("lbourdois/Qwen3-Embedding-dan-16384")
40
  # Run inference with queries and documents
41
  query = "My query"
42
  documents = [
 
24
  | **Vocabulary size** | 151,643 tokens | 16,384 tokens | **89.20%** |
25
  | **Model size** | 595,776,512 params | 457,244,672 params | **23.25%** |
26
 
 
27
 
28
  ## Mining Dataset Statistics
29
 
 
35
  ```python
36
  from sentence_transformers import SentenceTransformer
37
  # Download from the 🤗 Hub
38
+ model = SentenceTransformer("AlphaEdge-AI/Qwen3-Embedding-dan-16384")
39
  # Run inference with queries and documents
40
  query = "My query"
41
  documents = [
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "rms_norm_eps": 1e-06,
21
  "sliding_window": null,
22
  "tie_word_embeddings": true,
23
- "transformers_version": "5.0.0",
24
  "use_cache": true,
25
  "use_sliding_window": false,
26
  "vocab_size": 16384,
 
20
  "rms_norm_eps": 1e-06,
21
  "sliding_window": null,
22
  "tie_word_embeddings": true,
23
+ "transformers_version": "5.3.0.dev0",
24
  "use_cache": true,
25
  "use_sliding_window": false,
26
  "vocab_size": 16384,