srv-sngh's picture
Krill NVFP4 weights + card (current HumanEval numbers)
a6b2f18 verified
Raw
History Blame
10.7 kB
{
"architectures": [
"Gemma4UnifiedForConditionalGeneration"
],
"audio_config": {
"_name_or_path": "",
"architectures": null,
"audio_embed_dim": 640,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"model_type": "gemma4_unified_audio",
"output_attentions": false,
"output_hidden_states": false,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06
},
"audio_token_id": 258881,
"boa_token_id": 256000,
"boi_token_id": 255999,
"dtype": "bfloat16",
"eoa_token_index": 258883,
"eoi_token_id": 258882,
"eos_token_id": [
1,
106
],
"image_token_id": 258880,
"initializer_range": 0.02,
"model_type": "gemma4_unified",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attention_k_eq_v": true,
"bos_token_id": 2,
"dtype": "bfloat16",
"enable_moe_block": false,
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"global_head_dim": 512,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3840,
"hidden_size_per_layer_input": 0,
"initializer_range": 0.02,
"intermediate_size": 15360,
"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",
"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"
],
"max_position_embeddings": 262144,
"model_type": "gemma4_unified_text",
"moe_intermediate_size": null,
"num_attention_heads": 16,
"num_experts": null,
"num_global_key_value_heads": 1,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"num_kv_shared_layers": 0,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"partial_rotary_factor": 0.25,
"rope_theta": 1000000.0,
"rope_type": "proportional"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 1024,
"tie_word_embeddings": true,
"top_k_experts": null,
"use_bidirectional_attention": "vision",
"use_cache": true,
"use_double_wide_mlp": false,
"vocab_size": 262144,
"vocab_size_per_layer_input": 262144
},
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"video_token_id": 258884,
"vision_config": {
"_name_or_path": "",
"architectures": null,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"mm_embed_dim": 3840,
"mm_posemb_size": 1120,
"model_type": "gemma4_unified_vision",
"num_soft_tokens": 280,
"output_attentions": false,
"output_hidden_states": false,
"output_proj_dims": 3840,
"patch_size": 16,
"pooling_kernel_size": 3,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06
},
"torch_dtype": "bfloat16",
"quantization": {
"group_size": 16,
"bits": 4,
"mode": "nvfp4",
"language_model.model.layers.11.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.10.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.0.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.1.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"embed_audio.embedding_projection": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.2.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.19.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.17.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.14.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.15.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.18.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.13.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.16.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.12.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.28.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.27.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.26.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.25.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.23.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.22.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.21.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.24.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.20.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.29.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.32.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.34.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.31.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.35.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.36.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.3.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.33.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.30.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.44.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.43.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.42.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.40.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.38.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.4.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.39.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.41.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.37.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.9.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.8.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.45.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.7.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.47.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.6.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.46.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.5.self_attn.o_proj": {
"group_size": 64,
"bits": 8,
"mode": "affine"
}
}
}