seriouspark/gemma-7b-it-v0.3-lora-persona3_1000

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,11 +1,11 @@
 ---
-license: apache-2.0
+license: gemma
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-v0.3
+base_model: google/gemma-7b-it
 model-index:
 - name: outputs
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on an unknown dataset.
 
 ## Model description
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
+- lr_scheduler_warmup_steps: 0.1
 - training_steps: 1000
 - mixed_precision_training: Native AMP
 
@@ -51,6 +51,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.8.2
 - Transformers 4.39.0
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.2
+- Pytorch 2.1.2
+- Datasets 2.17.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "base_model_name_or_path": "google/gemma-7b-it",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
-    "up_proj",
-    "k_proj",
     "down_proj",
+    "k_proj",
     "gate_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a3146c6d1a6a4713e21d6478d6abf9e486e354a8671d293690e09776a5d97e
-size 335604696
+oid sha256:006742994fb5275114d730b60aa9aa85772e1da592dc7c2f7f0368a0bcf8b58e
+size 400084608

special_tokens_map.json

@@ -1,19 +1,29 @@
 {
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
   "bos_token": {
-    "content": "<s>",
+    "content": "<bos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6582ea9fca76fc160b1c888132f54dc25164e2779135b9e5f90b15d19359492
+oid sha256:5fab8376e19cee8dd432f485eaa9f3f0a8df8bb2de18c1d9b6ef5ab7c85e6e47
 size 4920