Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,4 +1,7 @@
 ---
+base_model: unsloth/mistral-7b-bnb-4bit
+datasets:
+- liyucheng/ShareGPT90K
 language:
 - en
 license: apache-2.0
@@ -9,9 +12,6 @@ tags:
 - mistral
 - trl
 - ollama
-base_model: unsloth/mistral-7b-bnb-4bit
-datasets:
-- liyucheng/ShareGPT90K
 ---
 
 # Uploaded  model

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "</s>",
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -134,10 +134,11 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,
-      "</s>": 2,
+      "<|im_end|>": 2,
       "<0x00>": 3,
       "<0x01>": 4,
       "<0x02>": 5,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -19,7 +20,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -27,16 +28,13 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|im_end|>",
   "legacy": true,
-  "model_max_length": 32768,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false