eskayML/mistral-7b-plaba-with-context

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/openhermes-2.5-mistral-7b-bnb-4bit
+base_model: unsloth/mistral-7b-bnb-4bit
 library_name: peft
 license: apache-2.0
 tags:
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [unsloth/openhermes-2.5-mistral-7b-bnb-4bit](https://huggingface.co/unsloth/openhermes-2.5-mistral-7b-bnb-4bit) on the None dataset.
+This model is a fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit) on the None dataset.
 
 ## Model description
 
@@ -37,15 +37,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 3407
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
-- training_steps: 100
+- training_steps: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/openhermes-2.5-mistral-7b-bnb-4bit",
+  "base_model_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
+    "o_proj",
+    "down_proj",
     "gate_proj",
-    "v_proj",
     "up_proj",
-    "o_proj",
-    "down_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bab43fb5454b1569a9a47e3df8c8ab0a46621f0b91463ebf680c5950587e16
+oid sha256:16d4ef93822fa31d6279f91dace055f3a17cf3610aa87577349b99b8774ef56e
 size 167832240

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_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>",
@@ -26,38 +26,19 @@
       "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": true
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "legacy": true,
+  "eos_token": "</s>",
+  "legacy": false,
   "model_max_length": 32768,
   "pad_token": "<unk>",
   "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": true,
-  "use_fast": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0b9c599d5e587a638a6fc4a17b90eb9ad02effca2bc13981be790a0611e419
+oid sha256:98ac43cfdbf19556a93042c8dea609ab8236bbb906076a8cde6df7f9748ad3d7
 size 5368