mrm8488 commited on
Commit
bd7f636
1 Parent(s): 2139af6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -24
README.md CHANGED
@@ -175,33 +175,23 @@ LINCE-ZERO was trained on AWS SageMaker, on ... GPUs in ... instances.
175
 
176
  ### Software
177
 
178
- More information needed
 
 
 
 
 
179
 
180
  # 🌳 Environmental Impact
181
 
182
  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
183
 
184
- - **Hardware Type:** More information needed
185
- - **Hours used:** More information needed
186
- - **Cloud Provider:** More information needed
187
- - **Compute Region:** More information needed
188
- - **Carbon Emitted:** More information needed
189
-
190
- # 📝 Citation
191
-
192
- There is a paper coming soon! Meanwhile, when using LINCE-ZERO please use the following information to cite:
193
-
194
- ```markdown
195
- @article{lince-zero,
196
- title={{LINCE-ZERO}: Llm for Instructions from Natural Corpus en Español},
197
- author={},
198
- year={2023}
199
- }
200
- ```
201
-
202
- # 📧 Contact
203
 
204
- [contacto@clibrain.com](mailto:contacto@clibrain.com)
205
 
206
  # 🔥 How to Get Started with LINCE-ZERO
207
 
@@ -213,7 +203,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer
213
 
214
  model_id = "clibrain/lince-zero"
215
 
216
- model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
217
  tokenizer = AutoTokenizer.from_pretrained(model_id)
218
 
219
  def create_instruction(instruction, input_data=None, context=None):
@@ -248,7 +238,7 @@ def generate(
248
  ):
249
 
250
  prompt = create_instruction(instruction, input, context)
251
- print(prompt)
252
  inputs = tokenizer(prompt, return_tensors="pt")
253
  input_ids = inputs["input_ids"].to("cuda")
254
  attention_mask = inputs["attention_mask"].to("cuda")
@@ -275,4 +265,20 @@ def generate(
275
 
276
  instruction = "Dame una lista de lugares a visitar en España."
277
  print(generate(instruction))
278
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
175
 
176
  ### Software
177
 
178
+ We used the following libraries:
179
+ - transformers
180
+ - accelerate
181
+ - peft
182
+ - bitsandbytes
183
+ - einops
184
 
185
  # 🌳 Environmental Impact
186
 
187
  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
188
 
189
+ - **Hardware Type:** 1 X A100 - 40 GB
190
+ - **Hours used:** 8
191
+ - **Cloud Provider:** Google
192
+ - **Compute Region:** Europe
193
+ - **Carbon Emitted:** 250W x 10h = 2.5 kWh x 0.57 kg eq. CO2/kWh = 1.42 kg eq. CO2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
194
 
 
195
 
196
  # 🔥 How to Get Started with LINCE-ZERO
197
 
 
203
 
204
  model_id = "clibrain/lince-zero"
205
 
206
+ model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).to("cuda")
207
  tokenizer = AutoTokenizer.from_pretrained(model_id)
208
 
209
  def create_instruction(instruction, input_data=None, context=None):
 
238
  ):
239
 
240
  prompt = create_instruction(instruction, input, context)
241
+ print(prompt.replace("### Respuesta:\n", "")
242
  inputs = tokenizer(prompt, return_tensors="pt")
243
  input_ids = inputs["input_ids"].to("cuda")
244
  attention_mask = inputs["attention_mask"].to("cuda")
 
265
 
266
  instruction = "Dame una lista de lugares a visitar en España."
267
  print(generate(instruction))
268
+ ```
269
+
270
+ # 📝 Citation
271
+
272
+ There is a paper coming soon! Meanwhile, when using LINCE-ZERO please use the following information to cite:
273
+
274
+ ```markdown
275
+ @article{lince-zero,
276
+ title={{LINCE-ZERO}: Llm for Instructions from Natural Corpus en Español},
277
+ author={},
278
+ year={2023}
279
+ }
280
+ ```
281
+
282
+ # 📧 Contact
283
+
284
+ [contacto@clibrain.com](mailto:contacto@clibrain.com)