Add files using upload-large-folder tool
Browse files- config.json +46 -0
 - merges.txt +0 -0
 - model-00004-of-00041.safetensors +3 -0
 - model-00006-of-00041.safetensors +3 -0
 - model-00015-of-00041.safetensors +3 -0
 - model-00016-of-00041.safetensors +3 -0
 - model-00022-of-00041.safetensors +3 -0
 - model-00037-of-00041.safetensors +3 -0
 
    	
        config.json
    ADDED
    
    | 
         @@ -0,0 +1,46 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "apply_layernorm_1p": true,
         
     | 
| 3 | 
         
            +
              "architectures": [
         
     | 
| 4 | 
         
            +
                "Qwen3NextForCausalLM"
         
     | 
| 5 | 
         
            +
              ],
         
     | 
| 6 | 
         
            +
              "attention_dropout": 0.0,
         
     | 
| 7 | 
         
            +
              "bos_token_id": 151643,
         
     | 
| 8 | 
         
            +
              "decoder_sparse_step": 1,
         
     | 
| 9 | 
         
            +
              "eos_token_id": 151643,
         
     | 
| 10 | 
         
            +
              "full_attention_interval": 4,
         
     | 
| 11 | 
         
            +
              "head_dim": 256,
         
     | 
| 12 | 
         
            +
              "hidden_act": "silu",
         
     | 
| 13 | 
         
            +
              "hidden_size": 2048,
         
     | 
| 14 | 
         
            +
              "initializer_range": 0.02,
         
     | 
| 15 | 
         
            +
              "intermediate_size": 5120,
         
     | 
| 16 | 
         
            +
              "linear_conv_kernel_dim": 4,
         
     | 
| 17 | 
         
            +
              "linear_expand_v": 1,
         
     | 
| 18 | 
         
            +
              "linear_key_head_dim": 128,
         
     | 
| 19 | 
         
            +
              "linear_num_key_heads": 16,
         
     | 
| 20 | 
         
            +
              "linear_num_value_heads": 32,
         
     | 
| 21 | 
         
            +
              "linear_value_head_dim": 128,
         
     | 
| 22 | 
         
            +
              "max_position_embeddings": 65536,
         
     | 
| 23 | 
         
            +
              "mlp_only_layers": [],
         
     | 
| 24 | 
         
            +
              "model_type": "qwen3_next",
         
     | 
| 25 | 
         
            +
              "moe_intermediate_size": 512,
         
     | 
| 26 | 
         
            +
              "norm_topk_prob": true,
         
     | 
| 27 | 
         
            +
              "num_attention_heads": 16,
         
     | 
| 28 | 
         
            +
              "num_experts": 512,
         
     | 
| 29 | 
         
            +
              "num_experts_per_tok": 10,
         
     | 
| 30 | 
         
            +
              "num_hidden_layers": 48,
         
     | 
| 31 | 
         
            +
              "num_key_value_heads": 2,
         
     | 
| 32 | 
         
            +
              "output_router_logits": false,
         
     | 
| 33 | 
         
            +
              "partial_rotary_factor": 0.25,
         
     | 
| 34 | 
         
            +
              "qkv_bias": false,
         
     | 
| 35 | 
         
            +
              "rms_norm_eps": 1e-06,
         
     | 
| 36 | 
         
            +
              "rope_scaling": null,
         
     | 
| 37 | 
         
            +
              "rope_theta": 10000000,
         
     | 
| 38 | 
         
            +
              "router_aux_loss_coef": 0.001,
         
     | 
| 39 | 
         
            +
              "shared_expert_intermediate_size": 512,
         
     | 
| 40 | 
         
            +
              "tie_word_embeddings": false,
         
     | 
| 41 | 
         
            +
              "torch_dtype": "bfloat16",
         
     | 
| 42 | 
         
            +
              "transformers_version": "4.56.0.dev0",
         
     | 
| 43 | 
         
            +
              "use_cache": true,
         
     | 
| 44 | 
         
            +
              "use_sliding_window": false,
         
     | 
| 45 | 
         
            +
              "vocab_size": 151936
         
     | 
| 46 | 
         
            +
            }
         
     | 
    	
        merges.txt
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         | 
    	
        model-00004-of-00041.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:91feebaeec4a30451d186c63a939331671f67c7b8f54fdfa443ae1e942e6bb74
         
     | 
| 3 | 
         
            +
            size 3999842000
         
     | 
    	
        model-00006-of-00041.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:4240714401dfc448b7d271c21f57d3e37e94fdb4cfe61fc52bc53b7a99157bd7
         
     | 
| 3 | 
         
            +
            size 3999853216
         
     | 
    	
        model-00015-of-00041.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:8690ccb1eb05c2ca89004aca4fcd61166720d9010bf87245fec9779b39964772
         
     | 
| 3 | 
         
            +
            size 4000181736
         
     | 
    	
        model-00016-of-00041.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:62c8c923584aa3aef52e09eb602a2157596c6a794bf83fe200eb1d674a6ec1b0
         
     | 
| 3 | 
         
            +
            size 3999517256
         
     | 
    	
        model-00022-of-00041.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:b3bafdaf9fb67877586bc9def63f1084f629ebb59ea26221c71548671be1ddc0
         
     | 
| 3 | 
         
            +
            size 3999843880
         
     | 
    	
        model-00037-of-00041.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:9739e815e66d118bbf21f47ae7d0552cd0b7086d6ada460883edfdea87e90162
         
     | 
| 3 | 
         
            +
            size 3999843872
         
     |