Nanbeige4.2-3B-MXFP8 / config.json
Osaurus-AI's picture
Nanbeige4.2-3B looped-transformer bundle (JANG)
4de465a verified
Raw
History Blame Contribute Delete
2.15 kB
{
"architectures": [
"NanbeigeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 166100,
"eos_token_id": 166101,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 10752,
"kv_channels": 128,
"loop_loss_weights": [],
"max_length": null,
"max_position_embeddings": 262144,
"model_type": "nanbeige",
"num_attention_heads": 48,
"num_hidden_layers": 22,
"num_key_value_heads": 8,
"num_loops": 2,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 70000000,
"skip_loop_final_norm": false,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.4",
"use_cache": true,
"vocab_size": 166144,
"weight_format": "mxfp8",
"quantization": {
"group_size": 32,
"bits": 8,
"mode": "mxfp8"
},
"jang_runtime": {
"architecture": "looped_transformer",
"cache_layout": "looped_kv_v1",
"num_loops": 2,
"num_hidden_layers": 22,
"cache_slots": 44,
"cache_slot_formula": "layer_idx + loop_idx * num_hidden_layers",
"loop_final_norm": "every_loop",
"shared_layer_weights_across_loops": true,
"position_ids_shared_across_loops": true,
"norm_convention": "llama_rmsnorm_no_plus_one",
"rope": {
"type": "neox_half_rotation",
"theta": 70000000,
"dims": 128,
"partial_rotary_factor": 1.0
},
"attention": {
"type": "gqa",
"n_heads": 48,
"n_kv_heads": 8,
"head_dim": 128,
"qkv_bias": false,
"qk_layernorm": false,
"n_heads_times_head_dim_equals_hidden": false
}
},
"capabilities": {
"reasoning_parser": "qwen3",
"tool_parser": "xml_function",
"think_in_template": true,
"supports_tools": true,
"supports_thinking": true,
"family": "nanbeige",
"modality": "text",
"modalities": {
"text": true,
"vision": false,
"audio": false,
"video": false
},
"has_vision": false,
"has_audio": false,
"has_video": false,
"cache_type": "kv"
}
}