Qwen2.5-14B-Instruct_16

README.md

@@ -28,7 +28,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/radchenko-pn-ukrainian-catholic-university/NER_SFT/runs/kkeqz91i) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/radchenko-pn-ukrainian-catholic-university/NER_SFT/runs/ax4zjmnd) 
 
 
 This model was trained with SFT.
@@ -36,7 +36,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.14.0
-- Transformers: 4.48.2
+- Transformers: 4.47.1
 - Pytorch: 2.5.1+cu124
 - Datasets: 3.2.0
 - Tokenizers: 0.21.0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "down_proj",
-    "up_proj",
+    "gate_proj",
     "q_proj",
+    "k_proj",
     "v_proj",
-    "gate_proj"
+    "up_proj",
+    "o_proj",
+    "down_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:c9ba8ee7db7d64cb147b96100c715853a311d619203c89e0e25bdae9b667a103
+oid sha256:422af23f4ae5b3b82d760f3506a9238e6846e74ca787b33b93de4e57a389c9f3
 size 275341720

added_tokens.json

@@ -1,7 +1,6 @@
 {
   "</tool_call>": 151658,
   "<tool_call>": 151657,
-  "<|PAD_TOKEN|>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|PAD_TOKEN|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
-size 11422086
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -177,14 +177,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "151665": {
-      "content": "<|PAD_TOKEN|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
@@ -209,7 +201,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,
-  "pad_token": "<|PAD_TOKEN|>",
+  "pad_token": "<|vision_pad|>",
   "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b433b835f9536a7c213aeab706e4d4119e9b7fefbe2b38a4a09dab94861835
+oid sha256:d9045f2a71bf96bc6d055f6e755138fc6861427ada644b759baf0b7465a54575
 size 5624