Bee-8B-RL / config.json
uyzhang's picture
Update README.md
052577a
{
"auto_map": {
"AutoConfig": "configuration_bee.BeeConfig",
"AutoModel": "modeling_bee.BeeForConditionalGeneration",
"AutoModelForCausalLM": "modeling_bee.BeeForConditionalGeneration"
},
"architectures": [
"BeeForConditionalGeneration"
],
"eos_token_id": 151645,
"image_grid_pinpoints": [
[
384,
384
],
[
384,
768
],
[
384,
1152
],
[
384,
1536
],
[
384,
1920
],
[
384,
2304
],
[
768,
384
],
[
768,
768
],
[
768,
1152
],
[
768,
1536
],
[
768,
1920
],
[
768,
2304
],
[
1152,
384
],
[
1152,
768
],
[
1152,
1152
],
[
1152,
1536
],
[
1152,
1920
],
[
1152,
2304
],
[
1536,
384
],
[
1536,
768
],
[
1536,
1152
],
[
1536,
1536
],
[
1536,
1920
],
[
1536,
2304
],
[
1920,
384
],
[
1920,
768
],
[
1920,
1152
],
[
1920,
1536
],
[
1920,
1920
],
[
1920,
2304
],
[
2304,
384
],
[
2304,
768
],
[
2304,
1152
],
[
2304,
1536
],
[
2304,
1920
],
[
2304,
2304
]
],
"image_token_index": 151669,
"model_type": "Bee",
"multimodal_projector_bias": true,
"pad_token_id": 151643,
"projector_hidden_act": "gelu",
"text_config": {
"_name_or_path": "Qwen/Qwen3-8B",
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"torch_dtype": "bfloat16",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152000
},
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.0",
"use_image_newline_parameter": true,
"video_token_index": 151670,
"vision_aspect_ratio": "anyres_max_6",
"vision_config": {
"auto_map": {
"AutoConfig": "configuration_bee.BeeConfig"
},
"attention_dropout": 0.0,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 26,
"patch_size": 14,
"torch_dtype": "bfloat16",
"vision_use_head": false
},
"vision_feature_layer": -1,
"vision_feature_select_strategy": "full"
}