Triangle104 commited on
Commit
90d2b32
1 Parent(s): e59b518

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md CHANGED
@@ -187,6 +187,73 @@ model-index:
187
  This model was converted to GGUF format from [`ValiantLabs/Llama3.1-8B-ShiningValiant2`](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
188
  Refer to the [original model card](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) for more details on the model.
189
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  ## Use with llama.cpp
191
  Install llama.cpp through brew (works on Mac and Linux)
192
 
 
187
  This model was converted to GGUF format from [`ValiantLabs/Llama3.1-8B-ShiningValiant2`](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
188
  Refer to the [original model card](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) for more details on the model.
189
 
190
+ ---
191
+ Model details:
192
+ -
193
+ Shining Valiant 2 is a chat model built on Llama 3.1 8b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
194
+
195
+ Finetuned on meta-llama/Meta-Llama-3.1-8B-Instruct for best available general performance
196
+ Trained on a variety of our high quality open source data; focused on science, engineering, technical knowledge, and structured reasoning
197
+ Also available for Llama 3.1 70b and Llama 3.2 3b!
198
+
199
+ Version
200
+ -
201
+ This is the 2024-11-04 release of Shining Valiant 2 for Llama 3.1 8b.
202
+
203
+ This release uses our newest datasets, open-sourced for everyone's use, including our expanded science-instruct dataset. This release features improvements in logical thinking and structured reasoning as well as physics, chemistry, biology, astronomy, Earth science, computer science, and information theory.
204
+
205
+ Future upgrades will continue to expand Shining Valiant's technical knowledge base.
206
+
207
+ Help us and recommend Shining Valiant 2 to your friends!
208
+
209
+ Prompting Guide
210
+
211
+ Shining Valiant 2 uses the Llama 3.1 Instruct prompt format. The example script below can be used as a starting point for general chat:
212
+
213
+ import transformers
214
+ import torch
215
+
216
+ model_id = "ValiantLabs/Llama3.1-8B-ShiningValiant2"
217
+
218
+ pipeline = transformers.pipeline(
219
+ "text-generation",
220
+ model=model_id,
221
+ model_kwargs={"torch_dtype": torch.bfloat16},
222
+ device_map="auto",
223
+ )
224
+
225
+ messages = [
226
+ {"role": "system", "content": "You are Shining Valiant, a highly capable chat AI."},
227
+ {"role": "user", "content": "Describe the role of transformation matrices in 3D graphics."}
228
+ ]
229
+
230
+ outputs = pipeline(
231
+ messages,
232
+ max_new_tokens=2048,
233
+ )
234
+
235
+ print(outputs[0]["generated_text"][-1])
236
+
237
+ The Model
238
+ -
239
+ Shining Valiant 2 is built on top of Llama 3.1 8b Instruct.
240
+
241
+ The current version of Shining Valiant 2 is trained on technical knowledge using sequelbox/Celestia, complex reasoning using sequelbox/Spurline, and general chat capability using sequelbox/Supernova.
242
+
243
+ We're super excited that Shining Valiant's dataset has been fully open-sourced! She's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical.
244
+
245
+
246
+ Shining Valiant 2 is created by Valiant Labs.
247
+
248
+ Check out our HuggingFace page for our open-source Build Tools models, including the newest version of code-specialist Enigma!
249
+
250
+ Follow us on X for updates on our models!
251
+
252
+ We care about open source. For everyone to use.
253
+
254
+ We encourage others to finetune further from our models.
255
+
256
+ ---
257
  ## Use with llama.cpp
258
  Install llama.cpp through brew (works on Mac and Linux)
259