Text Generation
Safetensors
English
llama
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-8b
llama-3
llama-3-instruct
llama-3-instruct-8b
8b
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct
Eval Results
c191b597e4415146f4bb0d3df015d2bd960a03ca7ee497671c00fa16ac390ee5
Browse files- .gitattributes +1 -0
- README.md +5 -4
- config.json +2 -1
- generation_config.json +1 -1
- 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-
|
| 265 |
|
| 266 |
-
|
| 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 |
-
|
| 309 |
|
| 310 |
|
| 311 |

|
|
|
|
| 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 |

|
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.
|
| 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.
|
| 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
|
|
|