diaratechHf_llama

README.md

@@ -1,14 +1,13 @@
 ---
-license: mit
+license: apache-2.0
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: microsoft/Phi-3-mini-128k-instruct
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 datasets:
 - generator
-pipeline_tag: text-generation
 model-index:
 - name: diaratechHf_llama
   results: []
@@ -19,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # diaratechHf_llama
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 
 ## Model description
 
@@ -56,5 +55,5 @@ The following hyperparameters were used during training:
 - PEFT 0.10.0
 - Transformers 4.40.1
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.0
+- Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "lm_head",
     "up_proj",
     "q_proj",
-    "o_proj",
+    "k_proj",
     "gate_proj",
-    "down_proj"
+    "lm_head",
+    "v_proj",
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616a01d54a824d93443dfd652074149207b9b9a6f92cd3e9dd621dc297068cf0
-size 545621264
+oid sha256:68a2bbd9f6fe4508ac71d8932067f3598fa1797e2c0e56815e742224665b16c4
+size 1204678496

special_tokens_map.json

@@ -7,13 +7,13 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -22,108 +22,21 @@
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "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": "<|endoftext|>",
-  "legacy": false,
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d723d5217803b087b5a3114f97a303aaf7c83fcf85c5234fe3b3ba9db45328
+oid sha256:b54ee5dfe7678e20a2032b08ad6d09aa31ce2f4e792a1de5c911588853f3dde5
 size 5048