More Pretraining on Knowledge Graphs for various situations to diversify planning abilities (^O_O ^)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TroyDoesAI/Mini-Llama",
+  "_name_or_path": ".\\BlackSheep",
   "architectures": [
     "MixtralForCausalLM"
   ],
@@ -15,7 +15,7 @@
   "mlp_bias": false,
   "model_type": "mixtral",
   "num_attention_heads": 32,
-  "num_experts_per_tok": 2,
+  "num_experts_per_tok": 1,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "num_local_experts": 4,
@@ -29,7 +29,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 32064
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02671e049890ba13c6378e4fa65f9a87bfbd903ac7989c51caa2be5fd4d9951a
-size 4999455976
+oid sha256:74e9ed9e85a8ec089dec78acaeafc1e275388b7a3b15c86e2b03f941617b4e4d
+size 4991365576

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbc53c2f2ce2a997680ef7ac3a1eaff6d6185acf6b4d30f80326fcf06ec0617
-size 4982948288
+oid sha256:75aa15ea9d57e719528dd64623018b092b7173d569872235dc17e56967b2e44e
+size 4995716136

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c71b3f036da5c8b4f9dcbf32e952661f8a4f42b484a4726f4ec26df592ce60
-size 4957769672
+oid sha256:d5f77982d537e4b22adc500503cb70d0da9956800b47efdc0674feec0b5ada9f
+size 4957942536

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada137083f86204ebba0f5b3cd341635f10b6c23047d104fa19459c984e93ab8
-size 4957769672
+oid sha256:bb371e4577e9915f9f6e34014581f24450d47588196e9cd7cfa3b031c15e3e70
+size 4995704008

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd99fd93c4fe483820829b61b7d28d0b94735eb89080f509bae8fa1937f11a8
-size 2240592528
+oid sha256:a0a158bd8f36eeef3813a4af5bc6338bc8139e70e6161432c4f6bd08919734f9
+size 2197808032

special_tokens_map.json

@@ -16,7 +16,13 @@
     "rstrip": true,
     "single_word": false
   },
-  "pad_token": "<s>",
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -339,8 +339,11 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|end|>",
   "legacy": false,
+  "max_length": null,
   "model_max_length": 4096,
+  "pad_to_multiple_of": null,
   "pad_token": "<s>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",