Upload folder using huggingface_hub

README.md

@@ -28,7 +28,7 @@ slices:
         layer_range: [0, 21]
         output_weight: 0.6
 merge_method: slerp
-base_model: cognitivecomputations/TinyDolphin-2.8-1.1b
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 parameters:
   t:
     - filter: self_attn

config.json

@@ -1,17 +1,17 @@
 {
-  "_name_or_path": "cognitivecomputations/TinyDolphin-2.8-1.1b",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
@@ -25,5 +25,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.4",
   "use_cache": true,
-  "vocab_size": 32002
+  "vocab_size": 32000
 }

mergekit_config.yml

@@ -8,7 +8,7 @@ slices:
         layer_range: [0, 21]
         output_weight: 0.6
 merge_method: slerp
-base_model: cognitivecomputations/TinyDolphin-2.8-1.1b
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 parameters:
   t:
     - filter: self_attn

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01fcd88232a151c4ad4f1295979447f9577e87e6182a411d00ea8c0006f9b208
+oid sha256:5f0eedd80e35d5a0751472c0995cbfd559707767246f2d7693b20b26f82bca88
 size 989934032

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fec467f693c2068e4e6ff2faab788146e226cf8e79567874e1b0f5b2cc70161
+oid sha256:194954945d7b17ba7346db8a3d6af80dac5effd8b8072c37d64e53064811d264
 size 992054392

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a48485d56c95525b28fb0cc03b2d2fe31a0cb975d12b3aa9fd9c037a90f8681
+oid sha256:a1da31f232f38a6d44a6f7c09ed213856f4e823f3ab4afd8240beff3c591d895
 size 130041616

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -29,33 +29,25 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 32000,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32001,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
     }
   ],
-  "normalizer": null,
-  "pre_tokenizer": {
-    "type": "Metaspace",
-    "replacement": "▁",
-    "prepend_scheme": "first",
-    "split": false
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Prepend",
+        "prepend": "▁"
+      },
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": " "
+        },
+        "content": "▁"
+      }
+    ]
   },
+  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -26,36 +26,18 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "</s>",
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 2048,
   "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "use_fast": true
+  "use_default_system_prompt": false
 }