[WIP] Upload folder using huggingface_hub (multi-commit eb71ae4c1e718d1dbc1682c4264be4bb3dc7dc948df9919b218bddc3bd69313f)

.gitattributes

@@ -33,4 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -29,7 +29,6 @@ tags:
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets:
 - sequelbox/Celestia
-- sequelbox/Spurline
 - sequelbox/Supernova
 model_type: llama
 model-index:
@@ -45,7 +44,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 75.85
+      value: 77.35
       name: acc
   - task:
       type: text-generation
@@ -57,7 +56,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 68.75
+      value: 76.39
       name: acc
   - task:
       type: text-generation
@@ -69,7 +68,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 73.23
+      value: 79.03
       name: acc
   - task:
       type: text-generation
@@ -81,7 +80,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 46.00
+      value: 50.0
       name: acc
   - task:
       type: text-generation
@@ -93,19 +92,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 44.33
-      name: acc
-  - task:
-      type: text-generation
-      name: Text Generation
-    dataset:
-      name: MMLU Conceptual Physics (5-Shot)
-      type: MMLU
-      args:
-        num_few_shot: 5
-    metrics:
-    - type: acc
-      value: 53.19
+      value: 53.2
       name: acc
   - task:
       type: text-generation
@@ -117,7 +104,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 37.25
+      value: 43.14
       name: acc
   - task:
       type: text-generation
@@ -141,7 +128,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 56.00
+      value: 55.0
       name: acc
   - task:
       type: text-generation
@@ -153,19 +140,19 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 63.00
+      value: 66.0
       name: acc
   - task:
       type: text-generation
       name: Text Generation
     dataset:
-      name: MMLU Astronomy (5-shot)
+      name: MMLU STEM (5-Shot)
       type: MMLU
       args:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 63.16
+      value: 55.57
       name: acc
   - task:
       type: text-generation
@@ -177,7 +164,7 @@ model-index:
         num_few_shot: 0
     metrics:
     - type: inst_level_strict_acc and prompt_level_strict_acc
-      value: 64.96
+      value: 65.24
       name: strict accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
@@ -207,7 +194,7 @@ model-index:
         num_few_shot: 4
     metrics:
     - type: exact_match
-      value: 12.92
+      value: 11.63
       name: exact match
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
@@ -222,7 +209,7 @@ model-index:
         num_few_shot: 0
     metrics:
     - type: acc_norm
-      value: 8.05
+      value: 8.95
       name: acc_norm
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
@@ -237,7 +224,7 @@ model-index:
         num_few_shot: 0
     metrics:
     - type: acc_norm
-      value: 7.46
+      value: 7.19
       name: acc_norm
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
@@ -254,7 +241,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 26.46
+      value: 26.38
       name: accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-ShiningValiant2
@@ -268,15 +255,14 @@ license: llama3.1
 
 Shining Valiant 2 is a chat model built on Llama 3.1 8b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
   - Finetuned on [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) for best available general performance
-  - Trained on a variety of our high quality open source data; focused on science, engineering, technical knowledge, and structured reasoning
-  - Also available for [Llama 3.1 70b](https://huggingface.co/ValiantLabs/Llama3.1-70B-ShiningValiant2) and [Llama 3.2 3b!](https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2)
+  - Trained on a variety of high quality data; focused on science, engineering, technical knowledge, and structured reasoning
 
 
 ## Version
 
-This is the **2024-11-04** release of Shining Valiant 2 for Llama 3.1 8b.
+This is the **2024-09-16** release of Shining Valiant 2 for Llama 3.1 8b.
 
-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.
+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.
 
 Future upgrades will continue to expand Shining Valiant's technical knowledge base.
 
@@ -316,9 +302,9 @@ print(outputs[0]["generated_text"][-1])
 ## The Model
 Shining Valiant 2 is built on top of Llama 3.1 8b Instruct.
 
-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)
+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)
 
-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.
+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!)
 
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)

config.json

@@ -11,7 +11,6 @@
     128008,
     128009
   ],
-  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -34,7 +33,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.1",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.46.1"
+  "transformers_version": "4.44.2"
 }

model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efbffa72857ec90e0ea4310a6025190a4e75eef43e10ec9d46025412e1616a8
+oid sha256:dcebe7b4eacb57cbc4e03e60f0d4e1eec8a1471455a3fdbc953edfaca5c8763e
 size 4886466168

model-00002-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c569b9d9276836eb9f31fda31ea667ee3ad1c132b852ec94b4b9a7a2598db0ca
+oid sha256:756b38e9412a00dc12d14823d48c9a71732a1c0318fd9bb48661e9589ddb9ac1
 size 4832007448

model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10413c97beeea538cb108448193c790d5224192982c2837b1dc3a54a1d5ff50b
+oid sha256:4d3ff8801d13032241f11b23af8bf458181a87b41b3e6497cf7cc503a0469ce6
 size 4999813112

model-00004-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef021115a20513e5b0db4178345a1f4959c59eb73fbb3679aca24055ead5d0e
+oid sha256:35ee4a044f0e1c92ba26c63b584ac344740d70fff1f3d86d073810bc8e610d66
 size 4999813128

model-00005-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26822b4a9c2cc0f9d92e0c1522f517aac4a20a6b936c706e1ca68ed1beaf8b44
+oid sha256:7b6123fecf735935528930e989780254f5bd5eb78b872cda5677f04479d09c25
 size 4832007496

model-00006-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f64f7cdbfd3903f7fea88117c49a8533a1ffa928d1ce4354d0d8431faddffe4
+oid sha256:895b3445cc9cb423b5c8b67c289eecd411f860ea3d7255857beb8fcb8e990621
 size 4999813120