Upload folder using huggingface_hub
Browse files- config.json +54 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +32 -0
- tokenizer.json +610 -0
- tokenizer_config.json +301 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3NextForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 257,
|
| 8 |
+
"decoder_sparse_step": 1,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 258,
|
| 11 |
+
"full_attention_interval": 4,
|
| 12 |
+
"head_dim": 64,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 2048,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"full_attention"
|
| 26 |
+
],
|
| 27 |
+
"linear_conv_kernel_dim": 4,
|
| 28 |
+
"linear_key_head_dim": 64,
|
| 29 |
+
"linear_num_key_heads": 12,
|
| 30 |
+
"linear_num_value_heads": 12,
|
| 31 |
+
"linear_value_head_dim": 64,
|
| 32 |
+
"max_position_embeddings": 262144,
|
| 33 |
+
"mlp_only_layers": [],
|
| 34 |
+
"model_type": "qwen3_next",
|
| 35 |
+
"moe_intermediate_size": 512,
|
| 36 |
+
"norm_topk_prob": true,
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_experts": 128,
|
| 39 |
+
"num_experts_per_tok": 4,
|
| 40 |
+
"num_hidden_layers": 8,
|
| 41 |
+
"num_key_value_heads": 2,
|
| 42 |
+
"output_router_logits": false,
|
| 43 |
+
"partial_rotary_factor": 0.25,
|
| 44 |
+
"rms_norm_eps": 1e-06,
|
| 45 |
+
"rope_scaling": null,
|
| 46 |
+
"rope_theta": 10000000,
|
| 47 |
+
"router_aux_loss_coef": 0.001,
|
| 48 |
+
"shared_expert_intermediate_size": 512,
|
| 49 |
+
"tie_word_embeddings": false,
|
| 50 |
+
"transformers_version": "4.57.0.dev0",
|
| 51 |
+
"use_cache": false,
|
| 52 |
+
"use_sliding_window": false,
|
| 53 |
+
"vocab_size": 288
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 257,
|
| 4 |
+
"eos_token_id": 258,
|
| 5 |
+
"transformers_version": "4.57.0.dev0",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b284fd57d27bb0a2a1c0964c39de34e9b9c35d23dc30bb2595629bd4aa482a47
|
| 3 |
+
size 2481263088
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|bos|>",
|
| 3 |
+
"eos_token": "<|eos|>",
|
| 4 |
+
"unk_token": "<|unk|>",
|
| 5 |
+
"pad_token": "<|pad|>",
|
| 6 |
+
"mask_token": "<|mask|>",
|
| 7 |
+
"additional_special_tokens": [
|
| 8 |
+
"<|reserved_265|>",
|
| 9 |
+
"<|reserved_266|>",
|
| 10 |
+
"<|reserved_267|>",
|
| 11 |
+
"<|reserved_268|>",
|
| 12 |
+
"<|reserved_269|>",
|
| 13 |
+
"<|reserved_270|>",
|
| 14 |
+
"<|reserved_271|>",
|
| 15 |
+
"<|reserved_272|>",
|
| 16 |
+
"<|reserved_273|>",
|
| 17 |
+
"<|reserved_274|>",
|
| 18 |
+
"<|reserved_275|>",
|
| 19 |
+
"<|reserved_276|>",
|
| 20 |
+
"<|reserved_277|>",
|
| 21 |
+
"<|reserved_278|>",
|
| 22 |
+
"<|reserved_279|>",
|
| 23 |
+
"<|reserved_280|>",
|
| 24 |
+
"<|reserved_281|>",
|
| 25 |
+
"<|reserved_282|>",
|
| 26 |
+
"<|reserved_283|>",
|
| 27 |
+
"<|reserved_284|>",
|
| 28 |
+
"<|reserved_285|>",
|
| 29 |
+
"<|reserved_286|>",
|
| 30 |
+
"<|reserved_287|>"
|
| 31 |
+
]
|
| 32 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 256,
|
| 8 |
+
"content": "<|pad|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 257,
|
| 17 |
+
"content": "<|bos|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 258,
|
| 26 |
+
"content": "<|eos|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 259,
|
| 35 |
+
"content": "<|unk|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 260,
|
| 44 |
+
"content": "<|mask|>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 261,
|
| 53 |
+
"content": "<|start_of_message|>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 262,
|
| 62 |
+
"content": "<|end_of_message|>",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 263,
|
| 71 |
+
"content": "<|start_of_thinking|>",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 264,
|
| 80 |
+
"content": "<|end_of_thinking|>",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 265,
|
| 89 |
+
"content": "<|reserved_265|>",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 266,
|
| 98 |
+
"content": "<|reserved_266|>",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 267,
|
| 107 |
+
"content": "<|reserved_267|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 268,
|
| 116 |
+
"content": "<|reserved_268|>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 269,
|
| 125 |
+
"content": "<|reserved_269|>",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 270,
|
| 134 |
+
"content": "<|reserved_270|>",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 271,
|
| 143 |
+
"content": "<|reserved_271|>",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 272,
|
| 152 |
+
"content": "<|reserved_272|>",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": false,
|
| 157 |
+
"special": true
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 273,
|
| 161 |
+
"content": "<|reserved_273|>",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": false,
|
| 166 |
+
"special": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 274,
|
| 170 |
+
"content": "<|reserved_274|>",
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"lstrip": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"special": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 275,
|
| 179 |
+
"content": "<|reserved_275|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": true
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 276,
|
| 188 |
+
"content": "<|reserved_276|>",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 277,
|
| 197 |
+
"content": "<|reserved_277|>",
|
| 198 |
+
"single_word": false,
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 278,
|
| 206 |
+
"content": "<|reserved_278|>",
|
| 207 |
+
"single_word": false,
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"normalized": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 279,
|
| 215 |
+
"content": "<|reserved_279|>",
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"lstrip": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"normalized": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 280,
|
| 224 |
+
"content": "<|reserved_280|>",
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"normalized": false,
|
| 229 |
+
"special": true
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 281,
|
| 233 |
+
"content": "<|reserved_281|>",
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"lstrip": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"special": true
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"id": 282,
|
| 242 |
+
"content": "<|reserved_282|>",
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"lstrip": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"special": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": 283,
|
| 251 |
+
"content": "<|reserved_283|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"id": 284,
|
| 260 |
+
"content": "<|reserved_284|>",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"id": 285,
|
| 269 |
+
"content": "<|reserved_285|>",
|
| 270 |
+
"single_word": false,
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"id": 286,
|
| 278 |
+
"content": "<|reserved_286|>",
|
| 279 |
+
"single_word": false,
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"normalized": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"id": 287,
|
| 287 |
+
"content": "<|reserved_287|>",
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"lstrip": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"normalized": false,
|
| 292 |
+
"special": true
|
| 293 |
+
}
|
| 294 |
+
],
|
| 295 |
+
"normalizer": null,
|
| 296 |
+
"pre_tokenizer": {
|
| 297 |
+
"type": "ByteLevel",
|
| 298 |
+
"add_prefix_space": false,
|
| 299 |
+
"trim_offsets": true,
|
| 300 |
+
"use_regex": true
|
| 301 |
+
},
|
| 302 |
+
"post_processor": null,
|
| 303 |
+
"decoder": {
|
| 304 |
+
"type": "ByteLevel",
|
| 305 |
+
"add_prefix_space": true,
|
| 306 |
+
"trim_offsets": true,
|
| 307 |
+
"use_regex": true
|
| 308 |
+
},
|
| 309 |
+
"model": {
|
| 310 |
+
"type": "BPE",
|
| 311 |
+
"dropout": null,
|
| 312 |
+
"unk_token": "<|unk|>",
|
| 313 |
+
"continuing_subword_prefix": null,
|
| 314 |
+
"end_of_word_suffix": null,
|
| 315 |
+
"fuse_unk": false,
|
| 316 |
+
"byte_fallback": false,
|
| 317 |
+
"ignore_merges": false,
|
| 318 |
+
"vocab": {
|
| 319 |
+
"Ā": 0,
|
| 320 |
+
"ā": 1,
|
| 321 |
+
"Ă": 2,
|
| 322 |
+
"ă": 3,
|
| 323 |
+
"Ą": 4,
|
| 324 |
+
"ą": 5,
|
| 325 |
+
"Ć": 6,
|
| 326 |
+
"ć": 7,
|
| 327 |
+
"Ĉ": 8,
|
| 328 |
+
"ĉ": 9,
|
| 329 |
+
"Ċ": 10,
|
| 330 |
+
"ċ": 11,
|
| 331 |
+
"Č": 12,
|
| 332 |
+
"č": 13,
|
| 333 |
+
"Ď": 14,
|
| 334 |
+
"ď": 15,
|
| 335 |
+
"Đ": 16,
|
| 336 |
+
"đ": 17,
|
| 337 |
+
"Ē": 18,
|
| 338 |
+
"ē": 19,
|
| 339 |
+
"Ĕ": 20,
|
| 340 |
+
"ĕ": 21,
|
| 341 |
+
"Ė": 22,
|
| 342 |
+
"ė": 23,
|
| 343 |
+
"Ę": 24,
|
| 344 |
+
"ę": 25,
|
| 345 |
+
"Ě": 26,
|
| 346 |
+
"ě": 27,
|
| 347 |
+
"Ĝ": 28,
|
| 348 |
+
"ĝ": 29,
|
| 349 |
+
"Ğ": 30,
|
| 350 |
+
"ğ": 31,
|
| 351 |
+
"Ġ": 32,
|
| 352 |
+
"!": 33,
|
| 353 |
+
"\"": 34,
|
| 354 |
+
"#": 35,
|
| 355 |
+
"$": 36,
|
| 356 |
+
"%": 37,
|
| 357 |
+
"&": 38,
|
| 358 |
+
"'": 39,
|
| 359 |
+
"(": 40,
|
| 360 |
+
")": 41,
|
| 361 |
+
"*": 42,
|
| 362 |
+
"+": 43,
|
| 363 |
+
",": 44,
|
| 364 |
+
"-": 45,
|
| 365 |
+
".": 46,
|
| 366 |
+
"/": 47,
|
| 367 |
+
"0": 48,
|
| 368 |
+
"1": 49,
|
| 369 |
+
"2": 50,
|
| 370 |
+
"3": 51,
|
| 371 |
+
"4": 52,
|
| 372 |
+
"5": 53,
|
| 373 |
+
"6": 54,
|
| 374 |
+
"7": 55,
|
| 375 |
+
"8": 56,
|
| 376 |
+
"9": 57,
|
| 377 |
+
":": 58,
|
| 378 |
+
";": 59,
|
| 379 |
+
"<": 60,
|
| 380 |
+
"=": 61,
|
| 381 |
+
">": 62,
|
| 382 |
+
"?": 63,
|
| 383 |
+
"@": 64,
|
| 384 |
+
"A": 65,
|
| 385 |
+
"B": 66,
|
| 386 |
+
"C": 67,
|
| 387 |
+
"D": 68,
|
| 388 |
+
"E": 69,
|
| 389 |
+
"F": 70,
|
| 390 |
+
"G": 71,
|
| 391 |
+
"H": 72,
|
| 392 |
+
"I": 73,
|
| 393 |
+
"J": 74,
|
| 394 |
+
"K": 75,
|
| 395 |
+
"L": 76,
|
| 396 |
+
"M": 77,
|
| 397 |
+
"N": 78,
|
| 398 |
+
"O": 79,
|
| 399 |
+
"P": 80,
|
| 400 |
+
"Q": 81,
|
| 401 |
+
"R": 82,
|
| 402 |
+
"S": 83,
|
| 403 |
+
"T": 84,
|
| 404 |
+
"U": 85,
|
| 405 |
+
"V": 86,
|
| 406 |
+
"W": 87,
|
| 407 |
+
"X": 88,
|
| 408 |
+
"Y": 89,
|
| 409 |
+
"Z": 90,
|
| 410 |
+
"[": 91,
|
| 411 |
+
"\\": 92,
|
| 412 |
+
"]": 93,
|
| 413 |
+
"^": 94,
|
| 414 |
+
"_": 95,
|
| 415 |
+
"`": 96,
|
| 416 |
+
"a": 97,
|
| 417 |
+
"b": 98,
|
| 418 |
+
"c": 99,
|
| 419 |
+
"d": 100,
|
| 420 |
+
"e": 101,
|
| 421 |
+
"f": 102,
|
| 422 |
+
"g": 103,
|
| 423 |
+
"h": 104,
|
| 424 |
+
"i": 105,
|
| 425 |
+
"j": 106,
|
| 426 |
+
"k": 107,
|
| 427 |
+
"l": 108,
|
| 428 |
+
"m": 109,
|
| 429 |
+
"n": 110,
|
| 430 |
+
"o": 111,
|
| 431 |
+
"p": 112,
|
| 432 |
+
"q": 113,
|
| 433 |
+
"r": 114,
|
| 434 |
+
"s": 115,
|
| 435 |
+
"t": 116,
|
| 436 |
+
"u": 117,
|
| 437 |
+
"v": 118,
|
| 438 |
+
"w": 119,
|
| 439 |
+
"x": 120,
|
| 440 |
+
"y": 121,
|
| 441 |
+
"z": 122,
|
| 442 |
+
"{": 123,
|
| 443 |
+
"|": 124,
|
| 444 |
+
"}": 125,
|
| 445 |
+
"~": 126,
|
| 446 |
+
"ġ": 127,
|
| 447 |
+
"Ģ": 128,
|
| 448 |
+
"ģ": 129,
|
| 449 |
+
"Ĥ": 130,
|
| 450 |
+
"ĥ": 131,
|
| 451 |
+
"Ħ": 132,
|
| 452 |
+
"ħ": 133,
|
| 453 |
+
"Ĩ": 134,
|
| 454 |
+
"ĩ": 135,
|
| 455 |
+
"Ī": 136,
|
| 456 |
+
"ī": 137,
|
| 457 |
+
"Ĭ": 138,
|
| 458 |
+
"ĭ": 139,
|
| 459 |
+
"Į": 140,
|
| 460 |
+
"į": 141,
|
| 461 |
+
"İ": 142,
|
| 462 |
+
"ı": 143,
|
| 463 |
+
"IJ": 144,
|
| 464 |
+
"ij": 145,
|
| 465 |
+
"Ĵ": 146,
|
| 466 |
+
"ĵ": 147,
|
| 467 |
+
"Ķ": 148,
|
| 468 |
+
"ķ": 149,
|
| 469 |
+
"ĸ": 150,
|
| 470 |
+
"Ĺ": 151,
|
| 471 |
+
"ĺ": 152,
|
| 472 |
+
"Ļ": 153,
|
| 473 |
+
"ļ": 154,
|
| 474 |
+
"Ľ": 155,
|
| 475 |
+
"ľ": 156,
|
| 476 |
+
"Ŀ": 157,
|
| 477 |
+
"ŀ": 158,
|
| 478 |
+
"Ł": 159,
|
| 479 |
+
"ł": 160,
|
| 480 |
+
"¡": 161,
|
| 481 |
+
"¢": 162,
|
| 482 |
+
"£": 163,
|
| 483 |
+
"¤": 164,
|
| 484 |
+
"¥": 165,
|
| 485 |
+
"¦": 166,
|
| 486 |
+
"§": 167,
|
| 487 |
+
"¨": 168,
|
| 488 |
+
"©": 169,
|
| 489 |
+
"ª": 170,
|
| 490 |
+
"«": 171,
|
| 491 |
+
"¬": 172,
|
| 492 |
+
"Ń": 173,
|
| 493 |
+
"®": 174,
|
| 494 |
+
"¯": 175,
|
| 495 |
+
"°": 176,
|
| 496 |
+
"±": 177,
|
| 497 |
+
"²": 178,
|
| 498 |
+
"³": 179,
|
| 499 |
+
"´": 180,
|
| 500 |
+
"µ": 181,
|
| 501 |
+
"¶": 182,
|
| 502 |
+
"·": 183,
|
| 503 |
+
"¸": 184,
|
| 504 |
+
"¹": 185,
|
| 505 |
+
"º": 186,
|
| 506 |
+
"»": 187,
|
| 507 |
+
"¼": 188,
|
| 508 |
+
"½": 189,
|
| 509 |
+
"¾": 190,
|
| 510 |
+
"¿": 191,
|
| 511 |
+
"À": 192,
|
| 512 |
+
"Á": 193,
|
| 513 |
+
"Â": 194,
|
| 514 |
+
"Ã": 195,
|
| 515 |
+
"Ä": 196,
|
| 516 |
+
"Å": 197,
|
| 517 |
+
"Æ": 198,
|
| 518 |
+
"Ç": 199,
|
| 519 |
+
"È": 200,
|
| 520 |
+
"É": 201,
|
| 521 |
+
"Ê": 202,
|
| 522 |
+
"Ë": 203,
|
| 523 |
+
"Ì": 204,
|
| 524 |
+
"Í": 205,
|
| 525 |
+
"Î": 206,
|
| 526 |
+
"Ï": 207,
|
| 527 |
+
"Ð": 208,
|
| 528 |
+
"Ñ": 209,
|
| 529 |
+
"Ò": 210,
|
| 530 |
+
"Ó": 211,
|
| 531 |
+
"Ô": 212,
|
| 532 |
+
"Õ": 213,
|
| 533 |
+
"Ö": 214,
|
| 534 |
+
"×": 215,
|
| 535 |
+
"Ø": 216,
|
| 536 |
+
"Ù": 217,
|
| 537 |
+
"Ú": 218,
|
| 538 |
+
"Û": 219,
|
| 539 |
+
"Ü": 220,
|
| 540 |
+
"Ý": 221,
|
| 541 |
+
"Þ": 222,
|
| 542 |
+
"ß": 223,
|
| 543 |
+
"à": 224,
|
| 544 |
+
"á": 225,
|
| 545 |
+
"â": 226,
|
| 546 |
+
"ã": 227,
|
| 547 |
+
"ä": 228,
|
| 548 |
+
"å": 229,
|
| 549 |
+
"æ": 230,
|
| 550 |
+
"ç": 231,
|
| 551 |
+
"è": 232,
|
| 552 |
+
"é": 233,
|
| 553 |
+
"ê": 234,
|
| 554 |
+
"ë": 235,
|
| 555 |
+
"ì": 236,
|
| 556 |
+
"í": 237,
|
| 557 |
+
"î": 238,
|
| 558 |
+
"ï": 239,
|
| 559 |
+
"ð": 240,
|
| 560 |
+
"ñ": 241,
|
| 561 |
+
"ò": 242,
|
| 562 |
+
"ó": 243,
|
| 563 |
+
"ô": 244,
|
| 564 |
+
"õ": 245,
|
| 565 |
+
"ö": 246,
|
| 566 |
+
"÷": 247,
|
| 567 |
+
"ø": 248,
|
| 568 |
+
"ù": 249,
|
| 569 |
+
"ú": 250,
|
| 570 |
+
"û": 251,
|
| 571 |
+
"ü": 252,
|
| 572 |
+
"ý": 253,
|
| 573 |
+
"þ": 254,
|
| 574 |
+
"ÿ": 255,
|
| 575 |
+
"<|pad|>": 256,
|
| 576 |
+
"<|bos|>": 257,
|
| 577 |
+
"<|eos|>": 258,
|
| 578 |
+
"<|unk|>": 259,
|
| 579 |
+
"<|mask|>": 260,
|
| 580 |
+
"<|start_of_message|>": 261,
|
| 581 |
+
"<|end_of_message|>": 262,
|
| 582 |
+
"<|start_of_thinking|>": 263,
|
| 583 |
+
"<|end_of_thinking|>": 264,
|
| 584 |
+
"<|reserved_265|>": 265,
|
| 585 |
+
"<|reserved_266|>": 266,
|
| 586 |
+
"<|reserved_267|>": 267,
|
| 587 |
+
"<|reserved_268|>": 268,
|
| 588 |
+
"<|reserved_269|>": 269,
|
| 589 |
+
"<|reserved_270|>": 270,
|
| 590 |
+
"<|reserved_271|>": 271,
|
| 591 |
+
"<|reserved_272|>": 272,
|
| 592 |
+
"<|reserved_273|>": 273,
|
| 593 |
+
"<|reserved_274|>": 274,
|
| 594 |
+
"<|reserved_275|>": 275,
|
| 595 |
+
"<|reserved_276|>": 276,
|
| 596 |
+
"<|reserved_277|>": 277,
|
| 597 |
+
"<|reserved_278|>": 278,
|
| 598 |
+
"<|reserved_279|>": 279,
|
| 599 |
+
"<|reserved_280|>": 280,
|
| 600 |
+
"<|reserved_281|>": 281,
|
| 601 |
+
"<|reserved_282|>": 282,
|
| 602 |
+
"<|reserved_283|>": 283,
|
| 603 |
+
"<|reserved_284|>": 284,
|
| 604 |
+
"<|reserved_285|>": 285,
|
| 605 |
+
"<|reserved_286|>": 286,
|
| 606 |
+
"<|reserved_287|>": 287
|
| 607 |
+
},
|
| 608 |
+
"merges": []
|
| 609 |
+
}
|
| 610 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 3 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
+
"padding_side": "right",
|
| 5 |
+
"truncation_side": "right",
|
| 6 |
+
"bos_token": "<|bos|>",
|
| 7 |
+
"eos_token": "<|eos|>",
|
| 8 |
+
"unk_token": "<|unk|>",
|
| 9 |
+
"pad_token": "<|pad|>",
|
| 10 |
+
"mask_token": "<|mask|>",
|
| 11 |
+
"add_bos_token": false,
|
| 12 |
+
"add_eos_token": false,
|
| 13 |
+
"clean_up_tokenization_spaces": true,
|
| 14 |
+
"legacy": false,
|
| 15 |
+
"name_or_path": "custom_autotokenizer_byte_tokenizer",
|
| 16 |
+
"trust_remote_code": false,
|
| 17 |
+
"use_fast": true,
|
| 18 |
+
"additional_special_tokens": [
|
| 19 |
+
"<|reserved_265|>",
|
| 20 |
+
"<|reserved_266|>",
|
| 21 |
+
"<|reserved_267|>",
|
| 22 |
+
"<|reserved_268|>",
|
| 23 |
+
"<|reserved_269|>",
|
| 24 |
+
"<|reserved_270|>",
|
| 25 |
+
"<|reserved_271|>",
|
| 26 |
+
"<|reserved_272|>",
|
| 27 |
+
"<|reserved_273|>",
|
| 28 |
+
"<|reserved_274|>",
|
| 29 |
+
"<|reserved_275|>",
|
| 30 |
+
"<|reserved_276|>",
|
| 31 |
+
"<|reserved_277|>",
|
| 32 |
+
"<|reserved_278|>",
|
| 33 |
+
"<|reserved_279|>",
|
| 34 |
+
"<|reserved_280|>",
|
| 35 |
+
"<|reserved_281|>",
|
| 36 |
+
"<|reserved_282|>",
|
| 37 |
+
"<|reserved_283|>",
|
| 38 |
+
"<|reserved_284|>",
|
| 39 |
+
"<|reserved_285|>",
|
| 40 |
+
"<|reserved_286|>",
|
| 41 |
+
"<|reserved_287|>"
|
| 42 |
+
],
|
| 43 |
+
"added_tokens_decoder": {
|
| 44 |
+
"256": {
|
| 45 |
+
"content": "<|pad|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"257": {
|
| 53 |
+
"content": "<|bos|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"258": {
|
| 61 |
+
"content": "<|eos|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"259": {
|
| 69 |
+
"content": "<|unk|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"260": {
|
| 77 |
+
"content": "<|mask|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"261": {
|
| 85 |
+
"content": "<|start_of_message|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"262": {
|
| 93 |
+
"content": "<|end_of_message|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"263": {
|
| 101 |
+
"content": "<|start_of_thinking|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"264": {
|
| 109 |
+
"content": "<|end_of_thinking|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"265": {
|
| 117 |
+
"content": "<|reserved_265|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"266": {
|
| 125 |
+
"content": "<|reserved_266|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"267": {
|
| 133 |
+
"content": "<|reserved_267|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"268": {
|
| 141 |
+
"content": "<|reserved_268|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"269": {
|
| 149 |
+
"content": "<|reserved_269|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"270": {
|
| 157 |
+
"content": "<|reserved_270|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"271": {
|
| 165 |
+
"content": "<|reserved_271|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"272": {
|
| 173 |
+
"content": "<|reserved_272|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"273": {
|
| 181 |
+
"content": "<|reserved_273|>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"274": {
|
| 189 |
+
"content": "<|reserved_274|>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"275": {
|
| 197 |
+
"content": "<|reserved_275|>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"276": {
|
| 205 |
+
"content": "<|reserved_276|>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"277": {
|
| 213 |
+
"content": "<|reserved_277|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"278": {
|
| 221 |
+
"content": "<|reserved_278|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"279": {
|
| 229 |
+
"content": "<|reserved_279|>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"280": {
|
| 237 |
+
"content": "<|reserved_280|>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"281": {
|
| 245 |
+
"content": "<|reserved_281|>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"282": {
|
| 253 |
+
"content": "<|reserved_282|>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"283": {
|
| 261 |
+
"content": "<|reserved_283|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"284": {
|
| 269 |
+
"content": "<|reserved_284|>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"285": {
|
| 277 |
+
"content": "<|reserved_285|>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"286": {
|
| 285 |
+
"content": "<|reserved_286|>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"287": {
|
| 293 |
+
"content": "<|reserved_287|>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
}
|
| 300 |
+
}
|
| 301 |
+
}
|