Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,6 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
| 34 |
"taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code"
|
| 35 |
)
|
| 36 |
|
| 37 |
-
|
| 38 |
if torch.cuda.is_available():
|
| 39 |
model = model.to("cuda")
|
| 40 |
|
|
@@ -54,8 +53,11 @@ outputs = model.generate(
|
|
| 54 |
repetition_penalty=1.1,
|
| 55 |
)
|
| 56 |
print(tokenizer.decode(outputs[0]))
|
|
|
|
| 57 |
|
| 58 |
-
|
|
|
|
|
|
|
| 59 |
<｜begin▁of▁sentence｜>You are an AI programming assistant, utilizing the DeepSeek Coder model, developed by DeepSeek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
|
| 60 |
### Instruction:
|
| 61 |
OpenCVを用いて定点カメラから画像を保存するコードを示してください。
|
|
@@ -76,8 +78,7 @@ cap.release()
|
|
| 76 |
cv2.destroyAllWindows()
|
| 77 |
```
|
| 78 |
<|EOT|>
|
| 79 |
-
|
| 80 |
-
|
| 81 |
|
| 82 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 83 |
|
|
|
|
| 34 |
"taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code"
|
| 35 |
)
|
| 36 |
|
|
|
|
| 37 |
if torch.cuda.is_available():
|
| 38 |
model = model.to("cuda")
|
| 39 |
|
|
|
|
| 53 |
repetition_penalty=1.1,
|
| 54 |
)
|
| 55 |
print(tokenizer.decode(outputs[0]))
|
| 56 |
+
```
|
| 57 |
|
| 58 |
+
# Output
|
| 59 |
+
|
| 60 |
+
````
|
| 61 |
<｜begin▁of▁sentence｜>You are an AI programming assistant, utilizing the DeepSeek Coder model, developed by DeepSeek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
|
| 62 |
### Instruction:
|
| 63 |
OpenCVを用いて定点カメラから画像を保存するコードを示してください。
|
|
|
|
| 78 |
cv2.destroyAllWindows()
|
| 79 |
```
|
| 80 |
<|EOT|>
|
| 81 |
+
````
|
|
|
|
| 82 |
|
| 83 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 84 |
|