Fixed config files to remove "is not compatible with the target model" error when using as draft in llama.cpp
Browse files- config.json +3 -30
- generation_config.json +1 -1
- tokenizer_config.json +48 -8
config.json
CHANGED
|
@@ -9,32 +9,6 @@
|
|
| 9 |
"hidden_size": 896,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 4864,
|
| 12 |
-
"layer_types": [
|
| 13 |
-
"full_attention",
|
| 14 |
-
"full_attention",
|
| 15 |
-
"full_attention",
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention"
|
| 37 |
-
],
|
| 38 |
"max_position_embeddings": 32768,
|
| 39 |
"max_window_layers": 21,
|
| 40 |
"model_type": "qwen2",
|
|
@@ -42,13 +16,12 @@
|
|
| 42 |
"num_hidden_layers": 24,
|
| 43 |
"num_key_value_heads": 2,
|
| 44 |
"rms_norm_eps": 1e-06,
|
| 45 |
-
"rope_scaling": null,
|
| 46 |
"rope_theta": 1000000.0,
|
| 47 |
-
"sliding_window":
|
| 48 |
"tie_word_embeddings": false,
|
| 49 |
"torch_dtype": "bfloat16",
|
| 50 |
-
"transformers_version": "4.
|
| 51 |
"use_cache": true,
|
| 52 |
"use_sliding_window": false,
|
| 53 |
"vocab_size": 163840
|
| 54 |
-
}
|
|
|
|
| 9 |
"hidden_size": 896,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 4864,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 32768,
|
| 13 |
"max_window_layers": 21,
|
| 14 |
"model_type": "qwen2",
|
|
|
|
| 16 |
"num_hidden_layers": 24,
|
| 17 |
"num_key_value_heads": 2,
|
| 18 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": 32768,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.43.1",
|
| 24 |
"use_cache": true,
|
| 25 |
"use_sliding_window": false,
|
| 26 |
"vocab_size": 163840
|
| 27 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"max_length":
|
| 3 |
"eos_token_id": 163586
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"max_length": 32768,
|
| 3 |
"eos_token_id": 163586
|
| 4 |
}
|
tokenizer_config.json
CHANGED
|
@@ -72,6 +72,46 @@
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
"163601": {
|
| 76 |
"content": "<|im_middle|>",
|
| 77 |
"lstrip": false,
|
|
@@ -107,12 +147,6 @@
|
|
| 107 |
"<|im_system|>",
|
| 108 |
"<|im_middle|>"
|
| 109 |
],
|
| 110 |
-
"auto_map": {
|
| 111 |
-
"AutoTokenizer": [
|
| 112 |
-
"tokenization_kimi.TikTokenTokenizer",
|
| 113 |
-
null
|
| 114 |
-
]
|
| 115 |
-
},
|
| 116 |
"bos_token": "[BOS]",
|
| 117 |
"clean_up_tokenization_spaces": false,
|
| 118 |
"eos_token": "[EOS]",
|
|
@@ -120,5 +154,11 @@
|
|
| 120 |
"model_max_length": 1000000000000000019884624838656,
|
| 121 |
"pad_token": "[PAD]",
|
| 122 |
"tokenizer_class": "TikTokenTokenizer",
|
| 123 |
-
"unk_token": "[UNK]"
|
| 124 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"single_word": false,
|
| 73 |
"special": true
|
| 74 |
},
|
| 75 |
+
"163595": {
|
| 76 |
+
"content": "<|tool_calls_section_begin|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"163596": {
|
| 84 |
+
"content": "<|tool_calls_section_end|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"163597": {
|
| 92 |
+
"content": "<|tool_call_begin|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"163598": {
|
| 100 |
+
"content": "<|tool_call_argument_begin|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"163599": {
|
| 108 |
+
"content": "<|tool_call_end|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
"163601": {
|
| 116 |
"content": "<|im_middle|>",
|
| 117 |
"lstrip": false,
|
|
|
|
| 147 |
"<|im_system|>",
|
| 148 |
"<|im_middle|>"
|
| 149 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
"bos_token": "[BOS]",
|
| 151 |
"clean_up_tokenization_spaces": false,
|
| 152 |
"eos_token": "[EOS]",
|
|
|
|
| 154 |
"model_max_length": 1000000000000000019884624838656,
|
| 155 |
"pad_token": "[PAD]",
|
| 156 |
"tokenizer_class": "TikTokenTokenizer",
|
| 157 |
+
"unk_token": "[UNK]",
|
| 158 |
+
"auto_map": {
|
| 159 |
+
"AutoTokenizer": [
|
| 160 |
+
"tokenization_kimi.TikTokenTokenizer",
|
| 161 |
+
null
|
| 162 |
+
]
|
| 163 |
+
}
|
| 164 |
+
}
|