Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "</think>": 166104,
+  "</tool_call>": 166106,
+  "<think>": 166103,
+  "<tool_call>": 166105,
+  "<|endoftext|>": 166102,
+  "<|im_end|>": 166101,
+  "<|im_start|>": 166100
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 166101,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10496,
+  "max_position_embeddings": 65536,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 166144
+}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8f0326910136aca20831249220b38ce5299527647bc8c6b65404485c479740
+size 18451122

tokenizer_config.json

@@ -0,0 +1,103 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166100": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166101": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166102": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166103": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166104": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166105": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166106": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "\n        {%- if tools %}\n            {{- '<|im_start|>system\n' }}\n            {%- if messages[0].role == 'system' %}\n                {{- messages[0].content + '\n\n' }}\n            {%- else %} \n                {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。\n如果没有一个函数可以使用，请直接使用自然语言回复用户。\n如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。\n如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} \n            {%- endif %}\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\n你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>\n' }} \n            {%- endif %}\n        {%- endif %}\n        {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n        {%- for message in messages[::-1] %}\n            {%- set index = (messages|length - 1) - loop.index0 %}\n            {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n                {%- set ns.multi_step_tool = false %}\n                {%- set ns.last_query_index = index %}\n            {%- endif %}\n        {%- endfor %}\n        {%- for message in messages %}\n            {%- if message.content is string %}\n                {%- set content = message.content %}\n            {%- else %}\n                {%- set content = '' %}\n            {%- endif %}\n            {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n                {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}\n            {%- elif message.role == \"assistant\" %}\n                {%- set reasoning_content = '' %}\n                {%- if message.reasoning_content is string %}\n                    {%- set reasoning_content = message.reasoning_content %}\n                {%- else %}\n                    {%- if '</think>' in content %}\n                        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}\n                        {%- set content = content.split('</think>')[-1].lstrip('\n') %}\n                    {%- endif %}\n                {%- endif %}\n                {%- if loop.index0 > ns.last_query_index %}\n                    {%- if loop.last or (not loop.last and reasoning_content) %}\n                        {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}\n                    {%- else %}\n                        {{- '<|im_start|>' + message.role + '\n' + content }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '<|im_start|>' + message.role + '\n' + content }}\n                {%- endif %}\n                {%- if message.tool_calls %}\n                    {%- for tool_call in message.tool_calls %}\n                        {%- if (loop.first and content) or (not loop.first) %}\n                            {{- '\n' }}\n                        {%- endif %}\n                        {%- if tool_call.function %}\n                            {%- set tool_call = tool_call.function %}\n                        {%- endif %}\n                        {{- '<tool_call>\n{\"name\": \"' }}\n                        {{- tool_call.name }}\n                        {{- '\", \"arguments\": ' }}\n                        {%- if tool_call.arguments is string %}\n                            {{- tool_call.arguments }}\n                        {%- else %}\n                            {{- tool_call.arguments | tojson }}\n                        {%- endif %}\n                        {{- '}\n</tool_call>' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '<|im_end|>\n' }}\n            {%- elif message.role == \"tool\" %}\n                {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n                    {{- '<|im_start|>user' }}\n                {%- endif %}\n                {{- '\n<tool_response>\n' }}\n                {{- 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",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}