End of training

README.md

@@ -1,11 +1,10 @@
 ---
-license: apache-2.0
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+base_model: TheBloke/saiga_mistral_7b-GPTQ
 model-index:
 - name: ayz_bot
   results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ayz_bot
 
-This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
+This model is a fine-tuned version of [TheBloke/saiga_mistral_7b-GPTQ](https://huggingface.co/TheBloke/saiga_mistral_7b-GPTQ) on the None dataset.
 
 ## Model description
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
+  "base_model_name_or_path": "TheBloke/saiga_mistral_7b-GPTQ",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab03b6483955be05745b61feb9133c11486459d9a05352371b7fde2b42abe3bb
+oid sha256:96b3fedb12858e5b92e8887a853d27408b83be36ac209e1bfb17d9b683d83166
 size 27280152

added_tokens.json

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

runs/Mar28_18-34-15_Sahib/events.out.tfevents.1711625655.Sahib.12248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6950dd362b9e376aebfe5e471d570a57962a36b9ddca71a4831056db4008b9e9
+size 11876

special_tokens_map.json

@@ -1,15 +1,20 @@
 {
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
@@ -17,7 +22,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -14,7 +14,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -32,8 +32,26 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": true,
+      "special": false
+    },
+    {
+      "id": 32001,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": {
@@ -56,12 +74,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -70,24 +82,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -95,17 +95,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -1,11 +1,11 @@
 {
-  "add_bos_token": true,
+  "add_bos_token": false,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,23 +21,43 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 32768,
   "pad_token": "</s>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a41b7059f78233f8ead463e41ea663b554eec64483ebebae72afd9a33e9d1c
+oid sha256:4e5885f0dab7b13121d6f1d357a85c0b42f6d3ad93845f728876296e96d1601c
 size 4920