Upload folder using huggingface_hub (#4)

- 546fc976bf5aa81ce15d5338dee87f2e82662464fa4564f6fdaf96c23547dc4a (2e19b2a8c9238863e5a558987a5523b54f5aa201)
- e3e3f20b79c580e59c52f28aa0e655ef60c2424c34d56582c3d94e131ecf5cea (a3720add28f15d4e2a40081ab84986d0de930a17)
- 805394328a1042e0ef1c1cd21b72d27f34ea42c7283da9ba3d4ec2222a515eee (ddf00ab8d6ededfde7188d9f7a7f5b0981693c0f)
- c922943291a6ec4c0c4e7848f08c4e9fe672df44da33b88c5783a6eedd022300 (5312a91dd59ac999d708965a4e69ed818196cf98)
- c00d881e95b6b548fbcad134d9187becb8341b02a7b88ca715789b9259472757 (5e7d15c626eb24fef3797402ebb7c843a75f91eb)
- faf3c310590cda877376f4e5174a30c1a6e174bba1ce80099ee2dc6543f15632 (1b91b2b1927ecf7a610c3fd24f431b9c9abd0493)
- 52d9f9a7423f67b048c1ac1d3d1f75430f1fd9236fb6990c8edbf406ba8ce009 (39fd75af1450fd3b11f63397b6194c231ac1e821)
- fa23febb535b1f8b6ce30b2b578b0341d82353104a3910625ff3e9128e8fd732 (83f6915f348ac64e59d7fea5cb9cfc0e60d5005c)
- 5c3d4717572dcffac59ece4429e85b1a5848d3ed8ccd1847c8bf470f2e91fdff (ab7609c6587406246fa1753761b2a380d8c277fa)
- 2d5194466aa9d1ed1d55c62532a9362cdb4c50e4356ee52451ca2888c5641a34 (944e3030731cb5493fc0027ead6f5c1f8ab60118)
- 252c4a42622684261eae15576fcf16ca645a1feec7a408658943c9ca0d3b039b (03328e734effdb05e944ed4ecb6292b7bc356399)
- a91634b4e42eeb457f4f2bcbe45807e668ed0469bdabfa82770d16c9750aeba2 (9d12ec089182bc20e08c3b7f957a161bd874b65c)
- svxs 1.2 (c2969b2056822b4ca26074336695daa6c50c2753)


Co-authored-by: scott <sequelbox@users.noreply.huggingface.co>

README.md

@@ -22,21 +22,19 @@ license: llama2
 Shining Valiant XS is a chat model built on the Llama 2 architecture, finetuned on our data for insight, creativity, passion, and friendliness.
   - Uses the llama-2-13b-chat model, with safetensors
   - Trained through multiple finetuning runs on public and private data
-  - the personality of our 70b [Shining Valiant](https://huggingface.co/ValiantLabs/ShiningValiant) model, now at 13b!
+  - the personality of our 70b [Shining Valiant](https://huggingface.co/ValiantLabs/ShiningValiant) model, now at 13b! **Our new release features greatly expanded personality capability**, bringing a more immersive chat experience!
 
 ## Version
 
-This is Version **1.1** of Shining Valiant XS.
+This is Version **1.2** of Shining Valiant XS. We've greatly expanded our personality dataset and fixed some bugs to deliver our strongest real-chat experience so far.
 
-Version 1.2 is now in training. (We're also exploring new models and architectures!)
+(We're also exploring **new models and architectures**, to deliver helpful open source capabilities for users and creators!)
 
-New models are released for everyone once our team's training and validation process is complete.
+Previous versions remain available in the repository. New models will be released for everyone once our team's training and validation process is complete.
 
 ## Evaluation
 
-| Model                 | Avg    | ARC   | HS    | MMLU   | TQA   | WG    | GSM   |
-|-----------------------|--------|-------|-------|--------|-------|-------|-------|
-| **Shining Valiant XS 1.1**   | 62.48  | 64.42 | 83.58 | 60.37  | 55.00 | 76.80 | 34.72 |
+Version 1.2 is awaiting evaluation from the Open LLM leaderboard.
 
 ## Prompting Guide
 Shining Valiant XS uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts!
@@ -49,13 +47,14 @@ A few examples of different formats:
 3. [INST] << SYS >> You are an intelligent, helpful AI assistant. << /SYS >> Deep dive about a country with interesting history: [/INST]
 
 ## The Model
-Shining Valiant XS is built on top of Dynamic Factor, which uses Llama 2's 13b parameter architecture and features upgraded general capability.
+Shining Valiant XS is built on top of Diamond Force, which uses Llama 2's 13b parameter architecture and features upgraded general and chat capability.
 
 From there, we've created Shining Valiant XS through multiple finetuning runs on different compositions of our private dataset, the same one we use for our [Shining Valiant](https://huggingface.co/ValiantLabs/ShiningValiant) model.
 
 Our private data focuses primarily on applying Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!
 
-We are actively working on expanding and improving the Shining Valiant dataset for use in future releases of the Shining Valiant series of models.
+With this release, the personality component of our Shining Valiant dataset has been greatly improved. We're excited to use it in future releases of this model and others.
+
 
 
 

config.json

@@ -4,6 +4,7 @@
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -21,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.36.2"
 }

model-00001-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbea3f185478945b995fa5e6b1add9060a4eaf66ed9a896c748ff6f5f8fe9e90
+oid sha256:28d5b463ecd9705bf8ff36f9277f542705a156488c90b1c721be43ce67db8ece
 size 4881247856

model-00002-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08089ea15764bff78da1c8c42c06094013d0297177b43ebf90d2f415b074a4a6
+oid sha256:515d77c185ef9baa8533c9b1385e7badc5804ff25ffc50b0fd47cb432f56bb7e
 size 4970418112

model-00003-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b5a4460d5568e13a16adc1cb8cdb187e66355b6ff92b45e6a5d37da07fbbb2
+oid sha256:2ceaa80bef149cabfef95bc60e3fe4d4045ebf41b8bcb19fcb89d419ba9093e3
 size 4970418120

model-00004-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd295baf8bc72183b0f86d854ff676031b4c740a9f92c747b3356b7b9702316
+oid sha256:4e505ba6f5d5c846323cc6a6583079e897480b12cf28818753613562343b2587
 size 4970418144

model-00005-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6bc44f0421d75b008fcb1fdc08a922706fd9c02f9abafcae87a7591645f28f2
+oid sha256:c3f32c59eadb9727df97a1022e674ac81a35fa241bbaf2ee2bccef3488994652
 size 4970418144

model-00006-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5637ee444eb11ea3fd796db547cf3e1c3e7d19714a2c55d67865d2e0245a1dc7
+oid sha256:4cd9753634daff9fcc2d9f0657a9cd79b2709c4010e1ace410fea7d3d103bc7e
 size 4792119040

model-00007-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834807fe9d3fa7a8f52e13d63403e9430a2ca24697f07cd8ca0521e80f5500b8
+oid sha256:d7c6a0a6abdbeca1931f1a9d2c0e9978a476c94e10cb7684c86baf7009323d57
 size 4792160232

model-00008-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b8a04a5243dab7b2a291e37f1064f1b70abe212a606bbcfed29a06ef7f9c89
+oid sha256:eabaebf9459de0b9b7312ffb94ed0b7f3bce8fe7a50fa01cd1b00b0da94809cd
 size 4792160224

model-00009-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b30ecef4c9d6c2f220c022ab3e954d1555bc423122857ade34f1386bc939130
+oid sha256:11108cbe989afd888d8719e61429b2e338a4ba8db2358a45a4aea2b692403945
 size 4970418144

model-00010-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312e0fffdd15b04ad78fac35c5241f3f649b3a17afa56b0410af6d63e852b072
+oid sha256:6b41b8ff5ee08a90f0801d5ac6376257f15aed1be420ade3a350eda4c7fbde9f
 size 4970418144

model-00011-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4aab365e7011a275a3f78a572c026ecdf4e85e793dd9c526423085c9173468
+oid sha256:4fc4abcff374606c356fd62724adef994779252ae66b2b03ad536905e3dea1cf
 size 2983303184

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,43 +1,35 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "legacy": false,
-  "max_length": 2048,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }