Text Generation
Transformers
Safetensors
Turkish
English
gemma3
image-text-to-text
chat
text-generation-inference
agent
cicikuş
cicikus
prettybird
bce
consciousness
conscious
llm
optimized
ethic
secure
turkish
english
behavioral-consciousness-engine
model
reasoning
think
thinking
chain-of-thought
STEM-expert
turkish & english
bce-aci
gemma
edge-ai
trl
unsloth
instruct
prometech
Prometheus
conversational
Eval Results (legacy)
| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.02, | |
| "boi_token_index": 255999, | |
| "bos_token_id": 2, | |
| "torch_dtype": "bfloat16", | |
| "eoi_token_index": 256000, | |
| "eos_token_id": 106, | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "mm_tokens_per_image": 256, | |
| "model_name": "/content/drive/MyDrive/pthinc/halftunedpofuduk", | |
| "model_type": "gemma3", | |
| "pad_token_id": 0, | |
| "text_config": { | |
| "_sliding_window_pattern": 6, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "torch_dtype": "bfloat16", | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "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", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "factor": 8.0, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "linear" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 1024, | |
| "sliding_window_pattern": 6, | |
| "tie_word_embeddings": true, | |
| "use_bidirectional_attention": false, | |
| "use_cache": true, | |
| "vocab_size": 262208 | |
| }, | |
| "tie_word_embeddings": true, | |
| "unsloth_fixed": true, | |
| "unsloth_version": "2026.3.15", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "torch_dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 896, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14, | |
| "vision_use_head": false | |
| } | |
| } |