NEXORA / reports /sources.json
devildasdf's picture
Release validated NEXORA research prototype, tiny weights and evidence
12496fc verified
Raw History Blame Contribute Delete
10.5 kB
{
"accessed_utc": "2026-09-28T13:00:06.286962+00:00",
"models": [
{
"repo": "Qwen/Qwen3-0.6B",
"revision": "c1899de289a04d12100db370d81485cdf75e47ca",
"license": "apache-2.0",
"config_url": "https://huggingface.co/Qwen/Qwen3-0.6B/resolve/c1899de289a04d12100db370d81485cdf75e47ca/config.json",
"card_url": "https://huggingface.co/Qwen/Qwen3-0.6B/blob/c1899de289a04d12100db370d81485cdf75e47ca/README.md",
"config": {
"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": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
},
{
"repo": "Qwen/Qwen3.5-0.8B",
"revision": "2fc06364715b967f1860aea9cf38778875588b17",
"license": "apache-2.0",
"config_url": "https://huggingface.co/Qwen/Qwen3.5-0.8B/resolve/2fc06364715b967f1860aea9cf38778875588b17/config.json",
"card_url": "https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/2fc06364715b967f1860aea9cf38778875588b17/README.md",
"config": {
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"image_token_id": 248056,
"model_type": "qwen3_5",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3584,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 16,
"linear_value_head_dim": 128,
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 8,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 248320,
"mamba_ssm_dtype": "float32",
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_type": "default",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25
}
},
"tie_word_embeddings": true,
"transformers_version": "4.57.0.dev0",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 12,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 768,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 3072,
"model_type": "qwen3_5",
"num_heads": 12,
"num_position_embeddings": 2304,
"out_hidden_size": 1024,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}
},
{
"repo": "Qwen/Qwen3.5-4B",
"revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
"license": "apache-2.0",
"config_url": "https://huggingface.co/Qwen/Qwen3.5-4B/resolve/851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a/config.json",
"card_url": "https://huggingface.co/Qwen/Qwen3.5-4B/blob/851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a/README.md",
"config": {
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"image_token_id": 248056,
"model_type": "qwen3_5",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9216,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 248320,
"mamba_ssm_dtype": "float32",
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_type": "default",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25
}
},
"tie_word_embeddings": true,
"transformers_version": "4.57.0.dev0",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 24,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1024,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4096,
"model_type": "qwen3_5",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2560,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}
},
{
"repo": "Qwen/Qwen3-30B-A3B-Instruct-2507",
"revision": "0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe",
"license": "apache-2.0",
"config_url": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/resolve/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/config.json",
"card_url": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/README.md",
"config": {
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 262144,
"max_window_layers": 48,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 768,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000000,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
}
]
}