dreamerdeo
commited on
Commit
•
20fd49c
1
Parent(s):
5831e6e
Update README.md
Browse files
README.md
CHANGED
@@ -51,7 +51,7 @@ The pre-training corpus heavily leverages the publicly available corpus, includi
|
|
51 |
[SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B),
|
52 |
[SkyPile](https://huggingface.co/datasets/Skywork/SkyPile-150B),
|
53 |
[CC100](https://huggingface.co/datasets/cc100) and [MADLAD-400](https://huggingface.co/datasets/allenai/MADLAD-400).
|
54 |
-
The instruction tuning corpus are all
|
55 |
[aya_collection](https://huggingface.co/datasets/CohereForAI/aya_collection),
|
56 |
[aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset),
|
57 |
[OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).
|
@@ -70,25 +70,42 @@ Here provides a code snippet to show you how to load the tokenizer and model and
|
|
70 |
|
71 |
```python
|
72 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
73 |
-
device = "cuda"
|
74 |
|
75 |
-
model = AutoModelForCausalLM.from_pretrained(
|
76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
-
|
79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
-
model_inputs = tokenizer([
|
|
|
82 |
|
83 |
generated_ids = model.generate(
|
84 |
-
|
85 |
-
max_new_tokens=
|
86 |
)
|
87 |
|
88 |
generated_ids = [
|
89 |
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
90 |
]
|
91 |
-
|
92 |
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
93 |
print(response)
|
94 |
```
|
|
|
51 |
[SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B),
|
52 |
[SkyPile](https://huggingface.co/datasets/Skywork/SkyPile-150B),
|
53 |
[CC100](https://huggingface.co/datasets/cc100) and [MADLAD-400](https://huggingface.co/datasets/allenai/MADLAD-400).
|
54 |
+
The instruction tuning corpus are all publicly available including
|
55 |
[aya_collection](https://huggingface.co/datasets/CohereForAI/aya_collection),
|
56 |
[aya_dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset),
|
57 |
[OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca).
|
|
|
70 |
|
71 |
```python
|
72 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
73 |
+
device = "cuda"
|
74 |
|
75 |
+
model = AutoModelForCausalLM.from_pretrained(
|
76 |
+
'sail/Sailor-1.8B-Chat',
|
77 |
+
torch_dtype="auto",
|
78 |
+
device_map="auto"
|
79 |
+
)
|
80 |
+
|
81 |
+
tokenizer = AutoTokenizer.from_pretrained('sail/Sailor-1.8B-Chat')
|
82 |
+
system_prompt= 'You are a helpful assistant'
|
83 |
+
|
84 |
+
prompt = "Beri saya pengenalan singkat tentang model bahasa besar."
|
85 |
+
# prompt = "Hãy cho tôi một giới thiệu ngắn gọn về mô hình ngôn ngữ lớn."
|
86 |
+
# prompt = "ให้ฉันแนะนำสั้น ๆ เกี่ยวกับโมเดลภาษาขนาดใหญ่"
|
87 |
|
88 |
+
messages = [
|
89 |
+
{"role": "system", "content": system_prompt},
|
90 |
+
{"role": "question", "content": prompt}
|
91 |
+
]
|
92 |
+
text = tokenizer.apply_chat_template(
|
93 |
+
messages,
|
94 |
+
tokenize=False,
|
95 |
+
add_generation_prompt=True
|
96 |
+
)
|
97 |
|
98 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
99 |
+
input_ids = model_inputs.input_ids.to(device)
|
100 |
|
101 |
generated_ids = model.generate(
|
102 |
+
input_ids,
|
103 |
+
max_new_tokens=512,
|
104 |
)
|
105 |
|
106 |
generated_ids = [
|
107 |
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
108 |
]
|
|
|
109 |
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
110 |
print(response)
|
111 |
```
|