cognitivess
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -153,5 +153,83 @@ print(tokenizer.decode(response, skip_special_tokens=True))
|
|
153 |
|
154 |
```
|
155 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
156 |
**Contact:**
|
157 |
<a href="mailto:hello@cognitivess.com">hello@cognitivess.com</a>
|
|
|
153 |
|
154 |
```
|
155 |
|
156 |
+
## Usage with LORA + Quantized Versions through bitsandbytes
|
157 |
+
|
158 |
+
To use this model, first install the custom package:
|
159 |
+
|
160 |
+
```bash
|
161 |
+
# Install required packages
|
162 |
+
!pip install git+https://huggingface.co/CognitivessAI/cognitivess
|
163 |
+
!pip install bitsandbytes
|
164 |
+
!pip install peft
|
165 |
+
|
166 |
+
```
|
167 |
+
|
168 |
+
Then, you can use the model like this:
|
169 |
+
```python
|
170 |
+
import cognitivess_model # Ensure this imports the custom model package
|
171 |
+
|
172 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
173 |
+
from peft import PeftModel, get_peft_config, LoraConfig
|
174 |
+
import torch
|
175 |
+
|
176 |
+
model_id = "CognitivessAI/cognitivess"
|
177 |
+
|
178 |
+
# Load the tokenizer
|
179 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
180 |
+
|
181 |
+
# Define the quantization configuration
|
182 |
+
quantization_config = {
|
183 |
+
"load_in_8bit": True,
|
184 |
+
"llm_int8_threshold": 6.0
|
185 |
+
}
|
186 |
+
|
187 |
+
# Load the model with 8-bit quantization
|
188 |
+
model = AutoModelForCausalLM.from_pretrained(
|
189 |
+
model_id,
|
190 |
+
torch_dtype=torch.float32,
|
191 |
+
device_map="auto",
|
192 |
+
**quantization_config
|
193 |
+
)
|
194 |
+
|
195 |
+
# Define the fine-tuning configuration
|
196 |
+
fine_tuning_config = LoraConfig(
|
197 |
+
r=8,
|
198 |
+
lora_alpha=16,
|
199 |
+
lora_dropout=0.1,
|
200 |
+
target_modules=["q_proj", "v_proj"]
|
201 |
+
)
|
202 |
+
|
203 |
+
# Apply parameter-efficient fine-tuning (PEFT) using QLoRA
|
204 |
+
model = PeftModel(model, fine_tuning_config)
|
205 |
+
|
206 |
+
# Prepare the messages
|
207 |
+
messages = [
|
208 |
+
{"role": "user", "content": "Explain how large language models work in detail."},
|
209 |
+
]
|
210 |
+
|
211 |
+
# Tokenize the input
|
212 |
+
input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
213 |
+
|
214 |
+
# Define the inference parameters
|
215 |
+
inference_params = {
|
216 |
+
"max_new_tokens": 8192,
|
217 |
+
"temperature": 0.7,
|
218 |
+
"top_p": 0.95,
|
219 |
+
"do_sample": True
|
220 |
+
}
|
221 |
+
|
222 |
+
# Generate the response
|
223 |
+
outputs = model.generate(
|
224 |
+
input_ids,
|
225 |
+
**inference_params
|
226 |
+
)
|
227 |
+
|
228 |
+
# Decode and print the response
|
229 |
+
response = outputs[0][input_ids.shape[-1]:]
|
230 |
+
print(tokenizer.decode(response, skip_special_tokens=True))
|
231 |
+
|
232 |
+
```
|
233 |
+
|
234 |
**Contact:**
|
235 |
<a href="mailto:hello@cognitivess.com">hello@cognitivess.com</a>
|