Jofthomas/gemma-2-2B-it-thinking-function_calling-V0

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: google/gemma-2-2b-it
+base_model: QCRI/Fanar-1-9B-Instruct
 library_name: transformers
 model_name: gemma-2-2B-it-thinking-function_calling-V0
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for gemma-2-2B-it-thinking-function_calling-V0
 
-This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it).
+This model is a fine-tuned version of [QCRI/Fanar-1-9B-Instruct](https://huggingface.co/QCRI/Fanar-1-9B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -34,9 +34,9 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.18.0
-- Transformers: 4.52.3
-- Pytorch: 2.7.0
+- TRL: 0.18.1
+- Transformers: 4.52.4
+- Pytorch: 2.7.1
 - Datasets: 3.6.0
 - Tokenizers: 0.21.1
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-2-2b-it",
+  "base_model_name_or_path": "QCRI/Fanar-1-9B-Instruct",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -24,15 +24,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "embed_tokens",
-    "gate_proj",
+    "lm_head",
     "k_proj",
+    "embed_tokens",
+    "down_proj",
+    "o_proj",
     "q_proj",
+    "gate_proj",
     "v_proj",
-    "lm_head",
-    "up_proj",
-    "o_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ace2d0713c369b1111a51dbe8b907ca893c3884ad908f5c5bfc94ed9633e59
-size 2475549872
+oid sha256:1dd592f48b190b9262a4cac71e0c38d219d3b7ee90d3c7b0f8750227d79549a3
+size 2071821368

added_tokens.json

@@ -1,10 +1,10 @@
 {
-  "</think>": 256003,
-  "</tool_call>": 256005,
-  "</tool_response>": 256007,
-  "</tools>": 256001,
-  "<think>": 256002,
-  "<tool_call>": 256004,
-  "<tool_response>": 256006,
-  "<tools>": 256000
+  "</think>": 128259,
+  "</tool_call>": 128261,
+  "</tool_response>": 128263,
+  "</tools>": 128257,
+  "<think>": 128258,
+  "<tool_call>": 128260,
+  "<tool_response>": 128262,
+  "<tools>": 128256
 }

runs/Jun11_05-56-03_c410f4ca4dc9/events.out.tfevents.1749621366.c410f4ca4dc9.704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cbfa539478b1b3b7aa78f606c00e3839df86277e8094fee87cd56aff51c1f6
+size 7312

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd8f004969d7a7c0b0d9b1c0d3335171bf05fd2e2bcf3066f780c9ad5b3fe99
-size 34364373
+oid sha256:1b0fce840be951700b72e7a32fc69f6fd9e7c801029b8a0277918f8151e51ce4
+size 18069535

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
-size 4241003
+oid sha256:c689fef08039792f515e5bcd67759b3bd73f845d8e7f0fda75471c6a103aad41
+size 2124704

tokenizer_config.json

@@ -1738,7 +1738,7 @@
       "single_word": false,
       "special": false
     },
-    "255968": {
+    "128224": {
       "content": "[toxicity=0]",
       "lstrip": false,
       "normalized": false,
@@ -1746,7 +1746,7 @@
       "single_word": false,
       "special": false
     },
-    "255969": {
+    "128225": {
       "content": "\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1754,7 +1754,7 @@
       "single_word": false,
       "special": false
     },
-    "255970": {
+    "128226": {
       "content": "\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1762,7 +1762,7 @@
       "single_word": false,
       "special": false
     },
-    "255971": {
+    "128227": {
       "content": "\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1770,7 +1770,7 @@
       "single_word": false,
       "special": false
     },
-    "255972": {
+    "128228": {
       "content": "\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1778,7 +1778,7 @@
       "single_word": false,
       "special": false
     },
-    "255973": {
+    "128229": {
       "content": "\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1786,7 +1786,7 @@
       "single_word": false,
       "special": false
     },
-    "255974": {
+    "128230": {
       "content": "\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1794,7 +1794,7 @@
       "single_word": false,
       "special": false
     },
-    "255975": {
+    "128231": {
       "content": "\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1802,7 +1802,7 @@
       "single_word": false,
       "special": false
     },
-    "255976": {
+    "128232": {
       "content": "\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1810,7 +1810,7 @@
       "single_word": false,
       "special": false
     },
-    "255977": {
+    "128233": {
       "content": "\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1818,7 +1818,7 @@
       "single_word": false,
       "special": false
     },
-    "255978": {
+    "128234": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1826,7 +1826,7 @@
       "single_word": false,
       "special": false
     },
-    "255979": {
+    "128235": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1834,7 +1834,7 @@
       "single_word": false,
       "special": false
     },
-    "255980": {
+    "128236": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1842,7 +1842,7 @@
       "single_word": false,
       "special": false
     },
-    "255981": {
+    "128237": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1850,7 +1850,7 @@
       "single_word": false,
       "special": false
     },
-    "255982": {
+    "128238": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1858,7 +1858,7 @@
       "single_word": false,
       "special": false
     },
-    "255983": {
+    "128239": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1866,7 +1866,7 @@
       "single_word": false,
       "special": false
     },
-    "255984": {
+    "128240": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1874,7 +1874,7 @@
       "single_word": false,
       "special": false
     },
-    "255985": {
+    "128241": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1882,7 +1882,7 @@
       "single_word": false,
       "special": false
     },
-    "255986": {
+    "128242": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1890,7 +1890,7 @@
       "single_word": false,
       "special": false
     },
-    "255987": {
+    "128243": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1898,7 +1898,7 @@
       "single_word": false,
       "special": false
     },
-    "255988": {
+    "128244": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1906,7 +1906,7 @@
       "single_word": false,
       "special": false
     },
-    "255989": {
+    "128245": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1914,7 +1914,7 @@
       "single_word": false,
       "special": false
     },
-    "255990": {
+    "128246": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1922,7 +1922,7 @@
       "single_word": false,
       "special": false
     },
-    "255991": {
+    "128247": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1930,7 +1930,7 @@
       "single_word": false,
       "special": false
     },
-    "255992": {
+    "128248": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1938,7 +1938,7 @@
       "single_word": false,
       "special": false
     },
-    "255993": {
+    "128249": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1946,7 +1946,7 @@
       "single_word": false,
       "special": false
     },
-    "255994": {
+    "128250": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1954,7 +1954,7 @@
       "single_word": false,
       "special": false
     },
-    "255995": {
+    "128251": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1962,7 +1962,7 @@
       "single_word": false,
       "special": false
     },
-    "255996": {
+    "128252": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1970,7 +1970,7 @@
       "single_word": false,
       "special": false
     },
-    "255997": {
+    "128253": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1978,7 +1978,7 @@
       "single_word": false,
       "special": false
     },
-    "255998": {
+    "128254": {
       "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": false,
@@ -1986,7 +1986,7 @@
       "single_word": false,
       "special": false
     },
-    "255999": {
+    "128255": {
       "content": "<unused99>",
       "lstrip": false,
       "normalized": false,
@@ -1994,7 +1994,7 @@
       "single_word": false,
       "special": false
     },
-    "256000": {
+    "128256": {
       "content": "<tools>",
       "lstrip": false,
       "normalized": false,
@@ -2002,7 +2002,7 @@
       "single_word": false,
       "special": true
     },
-    "256001": {
+    "128257": {
       "content": "</tools>",
       "lstrip": false,
       "normalized": false,
@@ -2010,7 +2010,7 @@
       "single_word": false,
       "special": true
     },
-    "256002": {
+    "128258": {
       "content": "<think>",
       "lstrip": false,
       "normalized": false,
@@ -2018,7 +2018,7 @@
       "single_word": false,
       "special": true
     },
-    "256003": {
+    "128259": {
       "content": "</think>",
       "lstrip": false,
       "normalized": false,
@@ -2026,7 +2026,7 @@
       "single_word": false,
       "special": true
     },
-    "256004": {
+    "128260": {
       "content": "<tool_call>",
       "lstrip": false,
       "normalized": false,
@@ -2034,7 +2034,7 @@
       "single_word": false,
       "special": true
     },
-    "256005": {
+    "128261": {
       "content": "</tool_call>",
       "lstrip": false,
       "normalized": false,
@@ -2042,7 +2042,7 @@
       "single_word": false,
       "special": true
     },
-    "256006": {
+    "128262": {
       "content": "<tool_response>",
       "lstrip": false,
       "normalized": false,
@@ -2050,7 +2050,7 @@
       "single_word": false,
       "special": true
     },
-    "256007": {
+    "128263": {
       "content": "</tool_response>",
       "lstrip": false,
       "normalized": false,
@@ -2077,8 +2077,10 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",
   "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:b68d94d3a198c58b76d2e6e69908cc405b4ff886116c10e586f704d7017c4792
+oid sha256:16f56f0696e1d1888e4ec399da4ea04d2ee0d1af7779f1570a80a942d614ec4e
 size 6097