Improve model card - Add pipeline tag, library name, link Github repository and project page

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +9 -16
README.md CHANGED
@@ -1,13 +1,16 @@
1
  ---
2
- license: apache-2.0
3
  language:
4
  - en
 
5
  metrics:
6
  - accuracy
7
  tags:
8
  - code
9
  arxiv: 2407.10424
 
 
10
  ---
 
11
  <div align="center">
12
  <img src="./assets/logo.png" style="zoom:25%;" />
13
  </div>
@@ -18,7 +21,6 @@ arxiv: 2407.10424
18
 
19
  CodeV is an innovative series of open-source, instruction-tuned Large Language Models (LLMs) specifically designed for the generation of high-quality Verilog code, addressing the challenges faced by existing models in this domain. **(This repo is under development)**
20
 
21
-
22
  ## Models and Datasets
23
 
24
  | | Base Model | CodeV |
@@ -38,35 +40,26 @@ from transformers import pipeline
38
 
39
  import torch
40
 
41
-
42
-
43
  prompt= "FILL IN THE QUESTION"
44
 
45
-
46
-
47
  generator = pipeline(
48
-
49
  model="CODEV",
50
-
51
  task="text-generation",
52
-
53
  torch_dtype=torch.bfloat16,
54
-
55
  device_map="auto",
56
-
57
  )
58
 
59
-
60
-
61
  result = generator(prompt , max_length=2048, num_return_sequences=1, temperature=0.0)
62
-
63
  response = result[0]["generated_text"]
64
-
65
  print("Response:", response)
66
  ```
67
  ## Paper
68
  **Arxiv:** <https://arxiv.org/abs/2407.10424>
69
 
 
 
 
 
70
  Please cite the paper if you use the models from CodeV.
71
 
72
  ```
@@ -85,4 +78,4 @@ Please cite the paper if you use the models from CodeV.
85
  * [Magicoder](https://github.com/ise-uiuc/magicoder): Training code, original datasets and data decontamination
86
  * [DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder): Base model for CodeV-DeepSeek
87
  * [CodeLlama](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/): Base model for CodeLlama
88
- * [CodeQwen](https://github.com/QwenLM/CodeQwen1.5): CodeV-CodeQwen
 
1
  ---
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
  metrics:
6
  - accuracy
7
  tags:
8
  - code
9
  arxiv: 2407.10424
10
+ library_name: transformers
11
+ pipeline_tag: text-generation
12
  ---
13
+
14
  <div align="center">
15
  <img src="./assets/logo.png" style="zoom:25%;" />
16
  </div>
 
21
 
22
  CodeV is an innovative series of open-source, instruction-tuned Large Language Models (LLMs) specifically designed for the generation of high-quality Verilog code, addressing the challenges faced by existing models in this domain. **(This repo is under development)**
23
 
 
24
  ## Models and Datasets
25
 
26
  | | Base Model | CodeV |
 
40
 
41
  import torch
42
 
 
 
43
  prompt= "FILL IN THE QUESTION"
44
 
 
 
45
  generator = pipeline(
 
46
  model="CODEV",
 
47
  task="text-generation",
 
48
  torch_dtype=torch.bfloat16,
 
49
  device_map="auto",
 
50
  )
51
 
 
 
52
  result = generator(prompt , max_length=2048, num_return_sequences=1, temperature=0.0)
 
53
  response = result[0]["generated_text"]
 
54
  print("Response:", response)
55
  ```
56
  ## Paper
57
  **Arxiv:** <https://arxiv.org/abs/2407.10424>
58
 
59
+ Project page: https://iprc-dip.github.io/CodeV-R1
60
+
61
+ Code: https://github.com/iprc-dip/CodeV
62
+
63
  Please cite the paper if you use the models from CodeV.
64
 
65
  ```
 
78
  * [Magicoder](https://github.com/ise-uiuc/magicoder): Training code, original datasets and data decontamination
79
  * [DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder): Base model for CodeV-DeepSeek
80
  * [CodeLlama](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/): Base model for CodeLlama
81
+ * [CodeQwen](https://github.com/QwenLM/CodeQwen1.5): CodeV-CodeQwen