初始化项目，由ModelHub XC社区提供模型

Model: Shahriar12354/testfahim
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+checkpoint-284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/gemma-3-270m-it
+library_name: transformers
+model_name: output
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for output
+
+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
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.1.0
+- Transformers: 5.0.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-284/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-284/config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "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_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

checkpoint-284/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "5.0.0"
+}

checkpoint-284/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18932534b14fbdeaba2cb8dd33a52e8a8c76ba207c75cc5c8644dcc1cea6078
+size 536223056

checkpoint-284/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30cfd239dd45f9c0b5f150ca6524c38c603c52a5fe9860fe385cd0fddcce1f9
+size 1546518667

checkpoint-284/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-284/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f38c137a365ec6f9e00fa0cd4932d42ec0e169efba559b60c69496c62fedda
+size 1465

checkpoint-284/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443

checkpoint-284/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-284/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 284,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.0583984375,
+      "epoch": 0.035211267605633804,
+      "grad_norm": 37.75,
+      "learning_rate": 1.9366197183098595e-05,
+      "loss": 1.7701053619384766,
+      "mean_token_accuracy": 0.6944564647972584,
+      "num_tokens": 7858.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.5865234375,
+      "epoch": 0.07042253521126761,
+      "grad_norm": 31.75,
+      "learning_rate": 1.8661971830985917e-05,
+      "loss": 0.42496376037597655,
+      "mean_token_accuracy": 0.9247574791312217,
+      "num_tokens": 13594.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.559375,
+      "epoch": 0.1056338028169014,
+      "grad_norm": 24.625,
+      "learning_rate": 1.7957746478873243e-05,
+      "loss": 0.3954581022262573,
+      "mean_token_accuracy": 0.9335559457540512,
+      "num_tokens": 19434.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.4927734375,
+      "epoch": 0.14084507042253522,
+      "grad_norm": 27.0,
+      "learning_rate": 1.7253521126760565e-05,
+      "loss": 0.3182990312576294,
+      "mean_token_accuracy": 0.9380857452750206,
+      "num_tokens": 25149.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.62119140625,
+      "epoch": 0.176056338028169,
+      "grad_norm": 26.875,
+      "learning_rate": 1.6549295774647887e-05,
+      "loss": 0.3523742437362671,
+      "mean_token_accuracy": 0.921422353386879,
+      "num_tokens": 31575.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.616943359375,
+      "epoch": 0.2112676056338028,
+      "grad_norm": 36.25,
+      "learning_rate": 1.5845070422535213e-05,
+      "loss": 0.26896488666534424,
+      "mean_token_accuracy": 0.9397121250629425,
+      "num_tokens": 36872.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.4833984375,
+      "epoch": 0.24647887323943662,
+      "grad_norm": 44.5,
+      "learning_rate": 1.5140845070422537e-05,
+      "loss": 0.3303802251815796,
+      "mean_token_accuracy": 0.9231527343392372,
+      "num_tokens": 43003.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.506201171875,
+      "epoch": 0.28169014084507044,
+      "grad_norm": 38.75,
+      "learning_rate": 1.443661971830986e-05,
+      "loss": 0.36821565628051756,
+      "mean_token_accuracy": 0.9252683132886886,
+      "num_tokens": 48605.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.64375,
+      "epoch": 0.31690140845070425,
+      "grad_norm": 33.5,
+      "learning_rate": 1.3732394366197184e-05,
+      "loss": 0.28042542934417725,
+      "mean_token_accuracy": 0.9455952301621438,
+      "num_tokens": 54883.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.44912109375,
+      "epoch": 0.352112676056338,
+      "grad_norm": 35.75,
+      "learning_rate": 1.3028169014084508e-05,
+      "loss": 0.2935742616653442,
+      "mean_token_accuracy": 0.935359711945057,
+      "num_tokens": 61415.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.38779296875,
+      "epoch": 0.3873239436619718,
+      "grad_norm": 21.625,
+      "learning_rate": 1.232394366197183e-05,
+      "loss": 0.28359940052032473,
+      "mean_token_accuracy": 0.942648071050644,
+      "num_tokens": 67390.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.53544921875,
+      "epoch": 0.4225352112676056,
+      "grad_norm": 34.0,
+      "learning_rate": 1.1619718309859156e-05,
+      "loss": 0.2355732202529907,
+      "mean_token_accuracy": 0.9371909454464913,
+      "num_tokens": 72616.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.603271484375,
+      "epoch": 0.45774647887323944,
+      "grad_norm": 26.75,
+      "learning_rate": 1.0915492957746481e-05,
+      "loss": 0.28939812183380126,
+      "mean_token_accuracy": 0.942104908823967,
+      "num_tokens": 78245.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.43603515625,
+      "epoch": 0.49295774647887325,
+      "grad_norm": 18.625,
+      "learning_rate": 1.0211267605633803e-05,
+      "loss": 0.31623306274414065,
+      "mean_token_accuracy": 0.9423870608210564,
+      "num_tokens": 84939.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.391650390625,
+      "epoch": 0.528169014084507,
+      "grad_norm": 25.875,
+      "learning_rate": 9.507042253521127e-06,
+      "loss": 0.24384639263153077,
+      "mean_token_accuracy": 0.9436959236860275,
+      "num_tokens": 90697.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.46484375,
+      "epoch": 0.5633802816901409,
+      "grad_norm": 36.25,
+      "learning_rate": 8.802816901408451e-06,
+      "loss": 0.273523736000061,
+      "mean_token_accuracy": 0.9429585993289947,
+      "num_tokens": 98163.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.57861328125,
+      "epoch": 0.5985915492957746,
+      "grad_norm": 23.5,
+      "learning_rate": 8.098591549295775e-06,
+      "loss": 0.2875859260559082,
+      "mean_token_accuracy": 0.9451341822743415,
+      "num_tokens": 104232.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.43037109375,
+      "epoch": 0.6338028169014085,
+      "grad_norm": 24.25,
+      "learning_rate": 7.3943661971831e-06,
+      "loss": 0.22526137828826903,
+      "mean_token_accuracy": 0.9523040130734444,
+      "num_tokens": 109993.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.50576171875,
+      "epoch": 0.6690140845070423,
+      "grad_norm": 13.9375,
+      "learning_rate": 6.690140845070423e-06,
+      "loss": 0.25973803997039796,
+      "mean_token_accuracy": 0.9431809738278389,
+      "num_tokens": 116723.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.63857421875,
+      "epoch": 0.704225352112676,
+      "grad_norm": 22.0,
+      "learning_rate": 5.9859154929577465e-06,
+      "loss": 0.20339107513427734,
+      "mean_token_accuracy": 0.9520902916789055,
+      "num_tokens": 123876.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.429931640625,
+      "epoch": 0.7394366197183099,
+      "grad_norm": 34.75,
+      "learning_rate": 5.28169014084507e-06,
+      "loss": 0.2633697032928467,
+      "mean_token_accuracy": 0.9487333759665489,
+      "num_tokens": 130683.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.46591796875,
+      "epoch": 0.7746478873239436,
+      "grad_norm": 33.0,
+      "learning_rate": 4.577464788732395e-06,
+      "loss": 0.277258563041687,
+      "mean_token_accuracy": 0.9407993748784065,
+      "num_tokens": 136650.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.404931640625,
+      "epoch": 0.8098591549295775,
+      "grad_norm": 19.75,
+      "learning_rate": 3.873239436619718e-06,
+      "loss": 0.20749433040618898,
+      "mean_token_accuracy": 0.9592674881219864,
+      "num_tokens": 142057.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.37626953125,
+      "epoch": 0.8450704225352113,
+      "grad_norm": 12.0,
+      "learning_rate": 3.1690140845070427e-06,
+      "loss": 0.2674617528915405,
+      "mean_token_accuracy": 0.9528747946023941,
+      "num_tokens": 146942.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.563525390625,
+      "epoch": 0.8802816901408451,
+      "grad_norm": 33.25,
+      "learning_rate": 2.4647887323943666e-06,
+      "loss": 0.2434919595718384,
+      "mean_token_accuracy": 0.9523143276572228,
+      "num_tokens": 153926.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.628564453125,
+      "epoch": 0.9154929577464789,
+      "grad_norm": 16.375,
+      "learning_rate": 1.7605633802816902e-06,
+      "loss": 0.1847941756248474,
+      "mean_token_accuracy": 0.9619321092963219,
+      "num_tokens": 160139.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.414111328125,
+      "epoch": 0.9507042253521126,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.0563380281690142e-06,
+      "loss": 0.14498558044433593,
+      "mean_token_accuracy": 0.9702936589717865,
+      "num_tokens": 164508.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.513232421875,
+      "epoch": 0.9859154929577465,
+      "grad_norm": 13.5625,
+      "learning_rate": 3.521126760563381e-07,
+      "loss": 0.23086421489715575,
+      "mean_token_accuracy": 0.9467697784304618,
+      "num_tokens": 170291.0,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 103970458857216.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-284/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938f66a5a8da1319ebf777e3c97b055f4c688463db8c2616b0a794f762a642ee
+size 5585

config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "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_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18932534b14fbdeaba2cb8dd33a52e8a8c76ba207c75cc5c8644dcc1cea6078
+size 536223056

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938f66a5a8da1319ebf777e3c97b055f4c688463db8c2616b0a794f762a642ee
+size 5585