Add 4-bit quantization and automatic device mapping for improved performance.
Browse filesMerhabalar, öncelikle tebrik ederim mükemmel bir çalışma olmuş, pull request olarak readme’e inference için 4 bit quantization ve modeli sistemdeki tüm ekran kartlarına ve rama otomatik yükleme kodu ekledim bu sayede kullanıcılar performans azalmadan daha hızlı ve verimli bir şekilde kullanabilirler.
README.md
CHANGED
@@ -63,3 +63,44 @@ generated_ids = model.generate(model_inputs,
|
|
63 |
decoded = tokenizer.batch_decode(generated_ids)
|
64 |
print(decoded[0])
|
65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
decoded = tokenizer.batch_decode(generated_ids)
|
64 |
print(decoded[0])
|
65 |
|
66 |
+
```
|
67 |
+
|
68 |
+
# 4-bit Quantized Inference
|
69 |
+
|
70 |
+
```python
|
71 |
+
|
72 |
+
# pip install bitsandbytes accelerate
|
73 |
+
|
74 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
|
75 |
+
import torch
|
76 |
+
|
77 |
+
quantization_config = BitsAndBytesConfig(
|
78 |
+
load_in_4bit=True,
|
79 |
+
bnb_4bit_quant_type="nf4",
|
80 |
+
bnb_4bit_use_double_quant=True,
|
81 |
+
bnb_4bit_compute_dtype=torch.float16 # or torch.bfloat16
|
82 |
+
)
|
83 |
+
|
84 |
+
model = AutoModelForCausalLM.from_pretrained("TURKCELL/Turkcell-LLM-7b-v1", device_map="auto", quantization_config=quantization_config)
|
85 |
+
tokenizer = AutoTokenizer.from_pretrained("TURKCELL/Turkcell-LLM-7b-v1")
|
86 |
+
|
87 |
+
messages = [
|
88 |
+
{"role": "user", "content": "Türkiye'nin başkenti neresidir?"},
|
89 |
+
]
|
90 |
+
|
91 |
+
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
|
92 |
+
|
93 |
+
eos_token = tokenizer("<|im_end|>",add_special_tokens=False)["input_ids"][0]
|
94 |
+
|
95 |
+
device = "cuda"
|
96 |
+
model_inputs = encodeds.to(device)
|
97 |
+
|
98 |
+
generated_ids = model.generate(model_inputs,
|
99 |
+
max_new_tokens=1024,
|
100 |
+
do_sample=True,
|
101 |
+
eos_token_id=eos_token)
|
102 |
+
|
103 |
+
decoded = tokenizer.batch_decode(generated_ids)
|
104 |
+
print(decoded[0])
|
105 |
+
|
106 |
+
```
|