Add library name and link to project page

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +7 -15
README.md CHANGED
@@ -1,12 +1,15 @@
1
  ---
2
- license: apache-2.0
3
  language:
4
  - en
 
5
  metrics:
6
  - accuracy
7
  tags:
8
  - code
 
 
9
  ---
 
10
  <div align="center">
11
  <img src="./assets/logo.png" style="zoom:25%;" />
12
  </div>
@@ -17,9 +20,11 @@ tags:
17
 
18
  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)**
19
 
 
 
20
  ## Models and Datasets
21
 
22
- | | Base Model | CodeV |
23
  | ---- | --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
24
  | 6.7B | [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) | [yang-z/CodeV-DS-6.7B](https://huggingface.co/yang-z/CodeV-DS-6.7B) |
25
  | 7B | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [yang-z/CodeV-CL-7B](https://huggingface.co/yang-z/CodeV-CL-7B) |
@@ -36,30 +41,17 @@ from transformers import pipeline
36
 
37
  import torch
38
 
39
-
40
-
41
  prompt= "FILL IN THE QUESTION"
42
 
43
-
44
-
45
  generator = pipeline(
46
-
47
  model="CODEV",
48
-
49
  task="text-generation",
50
-
51
  torch_dtype=torch.bfloat16,
52
-
53
  device_map="auto",
54
-
55
  )
56
 
57
-
58
-
59
  result = generator(prompt , max_length=2048, num_return_sequences=1, temperature=0.0)
60
-
61
  response = result[0]["generated_text"]
62
-
63
  print("Response:", response)
64
  ```
65
  ## Paper
 
1
  ---
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
  metrics:
6
  - accuracy
7
  tags:
8
  - code
9
+ pipeline_tag: text-generation
10
+ library_name: transformers
11
  ---
12
+
13
  <div align="center">
14
  <img src="./assets/logo.png" style="zoom:25%;" />
15
  </div>
 
20
 
21
  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)**
22
 
23
+ Project page: https://iprc-dip.github.io/CodeV-R1
24
+
25
  ## Models and Datasets
26
 
27
+ | | Base Model | CodeV |
28
  | ---- | --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
29
  | 6.7B | [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) | [yang-z/CodeV-DS-6.7B](https://huggingface.co/yang-z/CodeV-DS-6.7B) |
30
  | 7B | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [yang-z/CodeV-CL-7B](https://huggingface.co/yang-z/CodeV-CL-7B) |
 
41
 
42
  import torch
43
 
 
 
44
  prompt= "FILL IN THE QUESTION"
45
 
 
 
46
  generator = pipeline(
 
47
  model="CODEV",
 
48
  task="text-generation",
 
49
  torch_dtype=torch.bfloat16,
 
50
  device_map="auto",
 
51
  )
52
 
 
 
53
  result = generator(prompt , max_length=2048, num_return_sequences=1, temperature=0.0)
 
54
  response = result[0]["generated_text"]
 
55
  print("Response:", response)
56
  ```
57
  ## Paper