sequelbox commited on
Commit
5ab58aa
1 Parent(s): 23f25e7

c191b597e4415146f4bb0d3df015d2bd960a03ca7ee497671c00fa16ac390ee5

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. README.md +5 -4
  3. config.json +2 -1
  4. generation_config.json +1 -1
  5. tokenizer.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -29,6 +29,7 @@ tags:
29
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
30
  datasets:
31
  - sequelbox/Celestia
 
32
  - sequelbox/Supernova
33
  model_type: llama
34
  model-index:
@@ -261,9 +262,9 @@ Shining Valiant 2 is a chat model built on Llama 3.1 8b, finetuned on our data f
261
 
262
  ## Version
263
 
264
- This is the **2024-09-16** release of Shining Valiant 2 for Llama 3.1 8b.
265
 
266
- We've improved and open-sourced our new baseline [science-instruct dataset](https://huggingface.co/datasets/sequelbox/Celestia). This release features improvements in physics, chemistry, biology, and computer science.
267
 
268
  Future upgrades will continue to expand Shining Valiant's technical knowledge base.
269
 
@@ -303,9 +304,9 @@ print(outputs[0]["generated_text"][-1])
303
  ## The Model
304
  Shining Valiant 2 is built on top of Llama 3.1 8b Instruct.
305
 
306
- The current version of Shining Valiant 2 is trained on technical knowledge using [sequelbox/Celestia](https://huggingface.co/datasets/sequelbox/Celestia) and general chat capability using [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova)
307
 
308
- Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical. (As a general note: we're hoping to replace and open-source this part of Shining Valiant's dataset with synthetic data soon!)
309
 
310
 
311
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
 
29
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
30
  datasets:
31
  - sequelbox/Celestia
32
+ - sequelbox/Spurline
33
  - sequelbox/Supernova
34
  model_type: llama
35
  model-index:
 
262
 
263
  ## Version
264
 
265
+ This is the **2024-11-04** release of Shining Valiant 2 for Llama 3.1 8b.
266
 
267
+ This release uses our newest datasets, open-sourced for everyone's use, including our expanded [science-instruct dataset](https://huggingface.co/datasets/sequelbox/Celestia). This release features improvements in logical thinking and structured reasoning as well as physics, chemistry, biology, astronomy, Earth science, computer science, and information theory.
268
 
269
  Future upgrades will continue to expand Shining Valiant's technical knowledge base.
270
 
 
304
  ## The Model
305
  Shining Valiant 2 is built on top of Llama 3.1 8b Instruct.
306
 
307
+ The current version of Shining Valiant 2 is trained on technical knowledge using [sequelbox/Celestia](https://huggingface.co/datasets/sequelbox/Celestia), complex reasoning using [sequelbox/Spurline](https://huggingface.co/datasets/sequelbox/Spurline), and general chat capability using [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova)
308
 
309
+ 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.
310
 
311
 
312
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
config.json CHANGED
@@ -11,6 +11,7 @@
11
  128008,
12
  128009
13
  ],
 
14
  "hidden_act": "silu",
15
  "hidden_size": 4096,
16
  "initializer_range": 0.02,
@@ -33,7 +34,7 @@
33
  "rope_theta": 500000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.44.2",
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
 
11
  128008,
12
  128009
13
  ],
14
+ "head_dim": 128,
15
  "hidden_act": "silu",
16
  "hidden_size": 4096,
17
  "initializer_range": 0.02,
 
34
  "rope_theta": 500000.0,
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "float32",
37
+ "transformers_version": "4.46.1",
38
  "use_cache": true,
39
  "vocab_size": 128256
40
  }
generation_config.json CHANGED
@@ -8,5 +8,5 @@
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
- "transformers_version": "4.44.2"
12
  }
 
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
+ "transformers_version": "4.46.1"
12
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff