Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: google/gemma-3-270m-it
+base_model: google/gemma-3-1b-it
 library_name: transformers
 model_name: TAQ
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for TAQ
 
-This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
+This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -7,13 +7,17 @@
   "attention_dropout": 0.0,
   "attn_logit_softcapping": null,
   "bos_token_id": 2,
-  "eos_token_id": 1,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
   "final_logit_softcapping": null,
   "head_dim": 256,
   "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 640,
+  "hidden_size": 1152,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
+  "intermediate_size": 6912,
   "layer_types": [
     "sliding_attention",
     "sliding_attention",
@@ -32,23 +36,30 @@
     "sliding_attention",
     "sliding_attention",
     "sliding_attention",
-    "full_attention"
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
   ],
   "max_position_embeddings": 32768,
   "model_type": "gemma3_text",
   "num_attention_heads": 4,
-  "num_hidden_layers": 18,
+  "num_hidden_layers": 26,
   "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_local_base_freq": 10000,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
+  "rope_theta": 1000000,
   "sliding_window": 512,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.55.0",
-  "use_bidirectional_attention": false,
   "use_cache": true,
   "vocab_size": 262144
 }

generation_config.json

@@ -1,10 +1,12 @@
 {
+  "bos_token_id": 2,
   "cache_implementation": "hybrid",
   "do_sample": true,
   "eos_token_id": [
     1,
     106
   ],
+  "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
   "transformers_version": "4.55.0"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58c3392ff7f8e3b1378b5c489fd6a3860567307c84f3e0ad1e5e48355ecc606
-size 536223056
+oid sha256:f1783bf3418f6e5462bdd63c9a9c4bf18b591b680d6f1dec68acef8602c85942
+size 1999811208

runs/Aug15_14-15-41_ba4e9e7e48d5/events.out.tfevents.1755267357.ba4e9e7e48d5.259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cc2b066d5768b81172cd7a3daa018e0deb372ca53a8b2a779b83d226e90d40
+size 54138

tokenizer_config.json

@@ -51336,7 +51336,7 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "left",
+  "processor_class": "Gemma3Processor",
   "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:f018a955b9291428b4a6777ab3b1a0e726207c4fa24c61a486979219fabb9b55
+oid sha256:b9d2d47d2de69579741ebbf0156f9119d9d0f4b280094836ee5f3603a5b6e84e
 size 5816