Add library name and link to project page
#1
by
nielsr
HF Staff
- opened
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
|