Training in progress, epoch 1

README.md

@@ -1,18 +1,17 @@
 ---
-base_model: unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+base_model: google/gemma-3-270m-it
 library_name: transformers
 model_name: gemma3_google
 tags:
 - generated_from_trainer
 - sft
-- unsloth
 - trl
 licence: license
 ---
 
 # Model Card for gemma3_google
 
-This model is a fine-tuned version of [unsloth/gemma-3-270m-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/gemma-3-270m-it-unsloth-bnb-4bit).
+This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

chat_template.jinja

@@ -1,4 +1,3 @@
-{# Unsloth Chat template fixes #}
 {{ bos_token }}
 {%- if messages[0]['role'] == 'system' -%}
     {%- if messages[0]['content'] is string -%}
@@ -36,7 +35,7 @@
                 {{ item['text'] | trim }}
             {%- endif -%}
         {%- endfor -%}
-    {%- elif message['content'] is defined -%}
+    {%- else -%}
         {{ raise_exception("Invalid content type") }}
     {%- endif -%}
     {{ '<end_of_turn>
@@ -46,5 +45,3 @@
     {{'<start_of_turn>model
 '}}
 {%- endif -%}
-
-{# Copyright 2025-present Unsloth. Apache 2.0 License. #}

config.json

@@ -0,0 +1,54 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.4",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104b8549f162a63d119617d380924397a171e1d176031f2d3675490612e1762b
+size 536223056

special_tokens_map.json

@@ -8,13 +8,7 @@
     "single_word": false
   },
   "eoi_token": "<end_of_image>",
-  "eos_token": {
-    "content": "<end_of_turn>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<unk>",
   "image_token": "<image_soft_token>",
   "pad_token": {
     "content": "<pad>",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4201e7b539fef153e1fe3058db39e600717b3323fee690d37e92fa52fb2b5af2
-size 33384667
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer_config.json

@@ -51327,16 +51327,16 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
-  "eos_token": "<end_of_turn>",
+  "eos_token": "<unk>",
   "extra_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 32768,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "right",
+  "padding_side": "left",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0019a1c38be9c8f9f7bc8614804f41692bd819db8032ed5a8f05e867338b162
-size 6161
+oid sha256:e39c2a37b0c905ba449e92adf7640ddc18c58fb87820cc0fd725f173039c0524
+size 6289