Upload folder using huggingface_hub
Browse files- README.md +1 -1
- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- added_tokens.json +10 -22
- merges.txt +0 -0
- special_tokens_map.json +16 -17
- tokenizer.json +2 -2
- tokenizer_config.json +41 -137
- training_args.bin +1 -1
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -10,13 +10,13 @@
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
-
"lora_alpha":
|
| 14 |
-
"lora_dropout": 0.
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
-
"r":
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 144,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75ab9cc5620f8d9caad15c82412f8dbe18fc29ca877914e164a7f5cfe4fc2fca
|
| 3 |
+
size 142623480
|
added_tokens.json
CHANGED
|
@@ -1,24 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"<|
|
| 5 |
-
"<|
|
| 6 |
-
"<|
|
| 7 |
-
"<|
|
| 8 |
-
"<|
|
| 9 |
-
"<|
|
| 10 |
-
"<|
|
| 11 |
-
"<|
|
| 12 |
-
"<|im_end|>": 151645,
|
| 13 |
-
"<|im_start|>": 151644,
|
| 14 |
-
"<|image_pad|>": 151655,
|
| 15 |
-
"<|object_ref_end|>": 151647,
|
| 16 |
-
"<|object_ref_start|>": 151646,
|
| 17 |
-
"<|quad_end|>": 151651,
|
| 18 |
-
"<|quad_start|>": 151650,
|
| 19 |
-
"<|repo_name|>": 151663,
|
| 20 |
-
"<|video_pad|>": 151656,
|
| 21 |
-
"<|vision_end|>": 151653,
|
| 22 |
-
"<|vision_pad|>": 151654,
|
| 23 |
-
"<|vision_start|>": 151652
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<|/tool_call|>": 200026,
|
| 3 |
+
"<|/tool|>": 200024,
|
| 4 |
+
"<|assistant|>": 200019,
|
| 5 |
+
"<|end|>": 200020,
|
| 6 |
+
"<|system|>": 200022,
|
| 7 |
+
"<|tag|>": 200028,
|
| 8 |
+
"<|tool_call|>": 200025,
|
| 9 |
+
"<|tool_response|>": 200027,
|
| 10 |
+
"<|tool|>": 200023,
|
| 11 |
+
"<|user|>": 200021
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
}
|
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,25 +1,24 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"<|
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
"eos_token": {
|
| 18 |
-
"content": "<|
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": false,
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
-
"pad_token": "<|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
|
| 3 |
+
size 15524095
|
tokenizer_config.json
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
|
|
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
-
"
|
| 6 |
"content": "<|endoftext|>",
|
| 7 |
"lstrip": false,
|
| 8 |
"normalized": false,
|
|
@@ -10,200 +11,103 @@
|
|
| 10 |
"single_word": false,
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
-
"
|
| 14 |
-
"content": "<|
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
| 20 |
},
|
| 21 |
-
"
|
| 22 |
-
"content": "<|
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
-
"rstrip":
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
"single_word": false,
|
| 91 |
"special": true
|
| 92 |
},
|
| 93 |
-
"
|
| 94 |
-
"content": "<|
|
| 95 |
"lstrip": false,
|
| 96 |
"normalized": false,
|
| 97 |
-
"rstrip":
|
| 98 |
"single_word": false,
|
| 99 |
"special": true
|
| 100 |
},
|
| 101 |
-
"
|
| 102 |
-
"content": "<|
|
| 103 |
"lstrip": false,
|
| 104 |
"normalized": false,
|
| 105 |
-
"rstrip":
|
| 106 |
"single_word": false,
|
| 107 |
"special": true
|
| 108 |
},
|
| 109 |
-
"
|
| 110 |
-
"content": "<|
|
| 111 |
"lstrip": false,
|
| 112 |
"normalized": false,
|
| 113 |
-
"rstrip":
|
| 114 |
"single_word": false,
|
| 115 |
"special": true
|
| 116 |
},
|
| 117 |
-
"
|
| 118 |
-
"content": "
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
"lstrip": false,
|
| 136 |
"normalized": false,
|
| 137 |
-
"rstrip":
|
| 138 |
"single_word": false,
|
| 139 |
"special": false
|
| 140 |
},
|
| 141 |
-
"
|
| 142 |
-
"content": "
|
| 143 |
"lstrip": false,
|
| 144 |
"normalized": false,
|
| 145 |
-
"rstrip":
|
| 146 |
"single_word": false,
|
| 147 |
"special": false
|
| 148 |
},
|
| 149 |
-
"
|
| 150 |
-
"content": "<|
|
| 151 |
"lstrip": false,
|
| 152 |
"normalized": false,
|
| 153 |
-
"rstrip":
|
| 154 |
"single_word": false,
|
| 155 |
"special": false
|
| 156 |
},
|
| 157 |
-
"
|
| 158 |
-
"content": "
|
| 159 |
"lstrip": false,
|
| 160 |
"normalized": false,
|
| 161 |
-
"rstrip":
|
| 162 |
"single_word": false,
|
| 163 |
"special": false
|
| 164 |
},
|
| 165 |
-
"
|
| 166 |
-
"content": "<|
|
| 167 |
"lstrip": false,
|
| 168 |
"normalized": false,
|
| 169 |
-
"rstrip":
|
| 170 |
"single_word": false,
|
| 171 |
"special": false
|
| 172 |
},
|
| 173 |
-
"
|
| 174 |
-
"content": "<|
|
| 175 |
"lstrip": false,
|
| 176 |
"normalized": false,
|
| 177 |
-
"rstrip":
|
| 178 |
"single_word": false,
|
| 179 |
-
"special":
|
| 180 |
}
|
| 181 |
},
|
| 182 |
-
"
|
| 183 |
-
|
| 184 |
-
"<|im_end|>",
|
| 185 |
-
"<|object_ref_start|>",
|
| 186 |
-
"<|object_ref_end|>",
|
| 187 |
-
"<|box_start|>",
|
| 188 |
-
"<|box_end|>",
|
| 189 |
-
"<|quad_start|>",
|
| 190 |
-
"<|quad_end|>",
|
| 191 |
-
"<|vision_start|>",
|
| 192 |
-
"<|vision_end|>",
|
| 193 |
-
"<|vision_pad|>",
|
| 194 |
-
"<|image_pad|>",
|
| 195 |
-
"<|video_pad|>"
|
| 196 |
-
],
|
| 197 |
-
"bos_token": null,
|
| 198 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
-
"eos_token": "<|
|
| 201 |
-
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
"model_max_length": 131072,
|
| 204 |
-
"pad_token": "<|
|
| 205 |
"padding_side": "right",
|
| 206 |
-
"
|
| 207 |
-
"
|
| 208 |
-
"unk_token": null
|
| 209 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"add_prefix_space": false,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
+
"199999": {
|
| 7 |
"content": "<|endoftext|>",
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
|
|
|
| 11 |
"single_word": false,
|
| 12 |
"special": true
|
| 13 |
},
|
| 14 |
+
"200018": {
|
| 15 |
+
"content": "<|endofprompt|>",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
+
"200019": {
|
| 23 |
+
"content": "<|assistant|>",
|
| 24 |
"lstrip": false,
|
| 25 |
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
},
|
| 30 |
+
"200020": {
|
| 31 |
+
"content": "<|end|>",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
+
"rstrip": true,
|
| 35 |
"single_word": false,
|
| 36 |
"special": true
|
| 37 |
},
|
| 38 |
+
"200021": {
|
| 39 |
+
"content": "<|user|>",
|
| 40 |
"lstrip": false,
|
| 41 |
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
"single_word": false,
|
| 44 |
"special": true
|
| 45 |
},
|
| 46 |
+
"200022": {
|
| 47 |
+
"content": "<|system|>",
|
| 48 |
"lstrip": false,
|
| 49 |
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
"single_word": false,
|
| 52 |
"special": true
|
| 53 |
},
|
| 54 |
+
"200023": {
|
| 55 |
+
"content": "<|tool|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"lstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
"single_word": false,
|
| 60 |
"special": false
|
| 61 |
},
|
| 62 |
+
"200024": {
|
| 63 |
+
"content": "<|/tool|>",
|
| 64 |
"lstrip": false,
|
| 65 |
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
"single_word": false,
|
| 68 |
"special": false
|
| 69 |
},
|
| 70 |
+
"200025": {
|
| 71 |
+
"content": "<|tool_call|>",
|
| 72 |
"lstrip": false,
|
| 73 |
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
"single_word": false,
|
| 76 |
"special": false
|
| 77 |
},
|
| 78 |
+
"200026": {
|
| 79 |
+
"content": "<|/tool_call|>",
|
| 80 |
"lstrip": false,
|
| 81 |
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
"single_word": false,
|
| 84 |
"special": false
|
| 85 |
},
|
| 86 |
+
"200027": {
|
| 87 |
+
"content": "<|tool_response|>",
|
| 88 |
"lstrip": false,
|
| 89 |
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
"single_word": false,
|
| 92 |
"special": false
|
| 93 |
},
|
| 94 |
+
"200028": {
|
| 95 |
+
"content": "<|tag|>",
|
| 96 |
"lstrip": false,
|
| 97 |
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
}
|
| 102 |
},
|
| 103 |
+
"bos_token": "<|endoftext|>",
|
| 104 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
"clean_up_tokenization_spaces": false,
|
| 106 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
| 107 |
"extra_special_tokens": {},
|
| 108 |
"model_max_length": 131072,
|
| 109 |
+
"pad_token": "<|endoftext|>",
|
| 110 |
"padding_side": "right",
|
| 111 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 112 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
| 113 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d21651327b1966fc94a11991af1b1dacb90dfe6b15295b6872d36685933efff6
|
| 3 |
size 5560
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|