dariakryvosheieva commited on
Commit
834faeb
·
verified ·
1 Parent(s): 3eb8e13

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -14,14 +14,14 @@ license: cc-by-nc-4.0
14
  <b>The code embedding model trained by <a href="https://jina.ai/"><b>Jina AI</b></a>.</b>
15
  </p>
16
 
17
- # Jina Embeddings c1: A Small but Performant Code Embedding Model
18
 
19
  ## Intended Usage & Model Info
20
- `jina-embeddings-c1` is an embedding model for code retrieval.
21
  The model supports various types of code retrieval (text-to-code, code-to-code, code-to-text, code-to-completion) and technical question answering across 15+ programming languages.
22
 
23
 
24
- Built on [Qwen/Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B), `jina-embeddings-c1-0.5B` features:
25
 
26
  - **Multilingual support** (15+ programming languages) and compatibility with a wide range of domains, including web development, software development, machine learning, data science, and educational coding problems.
27
  - **Task-specific instruction prefixes** for NL2Code, Code2Code, Code2NL, Code2Completion, and Technical QA, which can be selected at inference time.
@@ -30,7 +30,7 @@ Built on [Qwen/Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5
30
 
31
  Summary of features:
32
 
33
- | Feature | Jina Embeddings C1 0.5B |
34
  |------------|------------|
35
  | Base Model | Qwen2.5-Coder-0.5B |
36
  | Supported Tasks | `nl2code`, `code2code`, `code2nl`, `code2completion`, `qa` |
@@ -66,7 +66,7 @@ from transformers import AutoModel
66
  import torch
67
 
68
  # Initialize the model
69
- model = AutoModel.from_pretrained("jinaai/jina-embeddings-c1-0.5B", trust_remote_code=True)
70
  model.to("cuda")
71
 
72
  # Configure truncate_dim, max_length, batch_size in the encode function if needed
@@ -98,7 +98,7 @@ from sentence_transformers import SentenceTransformer
98
 
99
  # Load the model
100
  model = SentenceTransformer(
101
- "jinaai/jina-embeddings-c1-0.5B",
102
  model_kwargs={
103
  "torch_dtype": torch.bfloat16,
104
  "attn_implementation": "flash_attention_2",
@@ -129,7 +129,7 @@ print(similarity)
129
 
130
  ## Training & Evaluation
131
 
132
- Please refer to our technical report of jina-embeddings-c1 for training details and benchmarks.
133
 
134
  ## Contact
135
 
 
14
  <b>The code embedding model trained by <a href="https://jina.ai/"><b>Jina AI</b></a>.</b>
15
  </p>
16
 
17
+ # Jina Code Embeddings: A Small but Performant Code Embedding Model
18
 
19
  ## Intended Usage & Model Info
20
+ `jina-code-embeddings` is an embedding model for code retrieval.
21
  The model supports various types of code retrieval (text-to-code, code-to-code, code-to-text, code-to-completion) and technical question answering across 15+ programming languages.
22
 
23
 
24
+ Built on [Qwen/Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B), `jina-code-embeddings-0.5b` features:
25
 
26
  - **Multilingual support** (15+ programming languages) and compatibility with a wide range of domains, including web development, software development, machine learning, data science, and educational coding problems.
27
  - **Task-specific instruction prefixes** for NL2Code, Code2Code, Code2NL, Code2Completion, and Technical QA, which can be selected at inference time.
 
30
 
31
  Summary of features:
32
 
33
+ | Feature | Jina Code Embeddings 0.5B |
34
  |------------|------------|
35
  | Base Model | Qwen2.5-Coder-0.5B |
36
  | Supported Tasks | `nl2code`, `code2code`, `code2nl`, `code2completion`, `qa` |
 
66
  import torch
67
 
68
  # Initialize the model
69
+ model = AutoModel.from_pretrained("jinaai/jina-code-embeddings-0.5b", trust_remote_code=True)
70
  model.to("cuda")
71
 
72
  # Configure truncate_dim, max_length, batch_size in the encode function if needed
 
98
 
99
  # Load the model
100
  model = SentenceTransformer(
101
+ "jinaai/jina-code-embeddings-0.5b",
102
  model_kwargs={
103
  "torch_dtype": torch.bfloat16,
104
  "attn_implementation": "flash_attention_2",
 
129
 
130
  ## Training & Evaluation
131
 
132
+ Please refer to our technical report of jina-code-embeddings for training details and benchmarks.
133
 
134
  ## Contact
135