Commit
•
c5f53e9
1
Parent(s):
d0ecaa0
Added code examples that correspond to each prompt format (#10)
Browse files- Added code examples that correspond to each prompt format (47518856bd4002238ea9cf400b0c34aa9346c352)
Co-authored-by: tim <macadeliccc@users.noreply.huggingface.co>
README.md
CHANGED
@@ -78,7 +78,46 @@ assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 42
|
|
78 |
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
|
79 |
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
|
80 |
```
|
|
|
81 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
## License
|
84 |
The dataset, model and online demo is a research preview intended for non-commercial use only, subject to the data distillation [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation.
|
|
|
78 |
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
|
79 |
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
|
80 |
```
|
81 |
+
## Code Examples
|
82 |
|
83 |
+
```python
|
84 |
+
import transformers
|
85 |
+
|
86 |
+
tokenizer = transformers.AutoTokenizer.from_pretrained("berkeley-nest/Starling-LM-7B-alpha")
|
87 |
+
model = transformers.AutoModelForCausalLM.from_pretrained("berkeley-nest/Starling-LM-7B-alpha")
|
88 |
+
|
89 |
+
def generate_response(prompt):
|
90 |
+
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
91 |
+
outputs = model.generate(
|
92 |
+
input_ids,
|
93 |
+
max_length=256,
|
94 |
+
pad_token_id=tokenizer.pad_token_id,
|
95 |
+
eos_token_id=tokenizer.eos_token_id,
|
96 |
+
)
|
97 |
+
response_ids = outputs[0]
|
98 |
+
response_text = tokenizer.decode(response_ids, skip_special_tokens=True)
|
99 |
+
return response_text
|
100 |
+
|
101 |
+
# Single-turn conversation
|
102 |
+
prompt = "Hello, how are you?"
|
103 |
+
single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
|
104 |
+
response_text = generate_response(single_turn_prompt)
|
105 |
+
print("Response:", response_text)
|
106 |
+
|
107 |
+
## Multi-turn conversation
|
108 |
+
prompt = "Hello"
|
109 |
+
follow_up_question = "How are you today?"
|
110 |
+
response = ""
|
111 |
+
multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:"
|
112 |
+
response_text = generate_response(multi_turn_prompt)
|
113 |
+
print("Multi-turn conversation response:", response_text)
|
114 |
+
|
115 |
+
### Coding conversation
|
116 |
+
prompt = "Implement quicksort using C++"
|
117 |
+
coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:"
|
118 |
+
response = generate_response(coding_prompt)
|
119 |
+
print("Coding conversation response:", response)
|
120 |
+
```
|
121 |
|
122 |
## License
|
123 |
The dataset, model and online demo is a research preview intended for non-commercial use only, subject to the data distillation [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation.
|