Upload folder using huggingface_hub

README.md

@@ -1,20 +1,20 @@
 ---
 base_model:
 - cognitivecomputations/TinyDolphin-2.8-1.1b
-- mbahrsnc/groot-1b
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
 - merge
 - mergekit
 - lazymergekit
 - cognitivecomputations/TinyDolphin-2.8-1.1b
-- mbahrsnc/groot-1b
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
 ---
 
 # mini-mcqueen
 
 mini-mcqueen is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [cognitivecomputations/TinyDolphin-2.8-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b)
-* [mbahrsnc/groot-1b](https://huggingface.co/mbahrsnc/groot-1b)
+* [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
 
 ## 🧩 Configuration
 
@@ -24,11 +24,11 @@ slices:
       - model: cognitivecomputations/TinyDolphin-2.8-1.1b
         layer_range: [0, 21]
         output_weight: 0.4
-      - model: mbahrsnc/groot-1b
+      - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
         layer_range: [0, 21]
         output_weight: 0.6
 merge_method: slerp
-base_model: mbahrsnc/groot-1b
+base_model: cognitivecomputations/TinyDolphin-2.8-1.1b
 parameters:
   t:
     - filter: self_attn

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -1,17 +1,17 @@
 {
-  "_name_or_path": "mbahrsnc/groot-1b",
+  "_name_or_path": "cognitivecomputations/TinyDolphin-2.8-1.1b",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 4096,
   "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": 32000
+  "vocab_size": 32002
 }

mergekit_config.yml

@@ -4,11 +4,11 @@ slices:
       - model: cognitivecomputations/TinyDolphin-2.8-1.1b
         layer_range: [0, 21]
         output_weight: 0.4
-      - model: mbahrsnc/groot-1b
+      - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
         layer_range: [0, 21]
         output_weight: 0.6
 merge_method: slerp
-base_model: mbahrsnc/groot-1b
+base_model: cognitivecomputations/TinyDolphin-2.8-1.1b
 parameters:
   t:
     - filter: self_attn

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aebd952d3c2245d8074c485432ee2546e17b8c155e79de150b9304fc5fbfdc9
+oid sha256:01fcd88232a151c4ad4f1295979447f9577e87e6182a411d00ea8c0006f9b208
 size 989934032

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26b9a37c6b47bfdc6c5f15acd255802a76fd3a88858cd52423d18635ee20dfb
+oid sha256:2fec467f693c2068e4e6ff2faab788146e226cf8e79567874e1b0f5b2cc70161
 size 992054392

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bee08bbf2398f2ddc5e332a9407f7ade4f8b210874d41f2df16ab59ae303845
+oid sha256:0a48485d56c95525b28fb0cc03b2d2fe31a0cb975d12b3aa9fd9c037a90f8681
 size 130041616

special_tokens_map.json

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

tokenizer.json

@@ -29,25 +29,33 @@
       "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": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "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": null,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -26,18 +26,36 @@
       "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": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": false,
-  "model_max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
   "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_default_system_prompt": false,
+  "use_fast": true
 }