(Trained with Unsloth)
Browse files- .gitattributes +1 -0
- chat_template.jinja +101 -0
- config.json +121 -0
- generation_config.json +8 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +247 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if not add_generation_prompt is defined %}
|
| 2 |
+
{%- set add_generation_prompt = false %}
|
| 3 |
+
{%- endif %}
|
| 4 |
+
{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
|
| 5 |
+
{%- for message in messages %}
|
| 6 |
+
{%- if message['role'] == 'system' %}
|
| 7 |
+
{%- if ns.is_first_sp %}
|
| 8 |
+
{%- set ns.system_prompt = ns.system_prompt + message['content'] %}
|
| 9 |
+
{%- set ns.is_first_sp = false %}
|
| 10 |
+
{%- else %}
|
| 11 |
+
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endfor %}
|
| 15 |
+
|
| 16 |
+
{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
|
| 17 |
+
{%- if tools is defined and tools is not none %}
|
| 18 |
+
{%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
|
| 19 |
+
{%- for tool in tools %}
|
| 20 |
+
{%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
|
| 21 |
+
{%- endfor %}
|
| 22 |
+
{%- if ns.system_prompt|length != 0 %}
|
| 23 |
+
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
|
| 24 |
+
{%- else %}
|
| 25 |
+
{%- set ns.system_prompt = tool_ns.text %}
|
| 26 |
+
{%- endif %}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{{- bos_token }}
|
| 29 |
+
{{- ns.system_prompt }}
|
| 30 |
+
{%- set last_index = (messages|length - 1) %}
|
| 31 |
+
{%- for message in messages %}
|
| 32 |
+
{%- set content = message['content'] %}
|
| 33 |
+
{%- if message['role'] == 'user' %}
|
| 34 |
+
{%- set ns.is_tool = false -%}
|
| 35 |
+
{%- set ns.is_first = false -%}
|
| 36 |
+
{%- set ns.is_last_user = true -%}
|
| 37 |
+
{%- if loop.index0 == last_index %}
|
| 38 |
+
{{- '<｜User｜>' + content }}
|
| 39 |
+
{%- else %}
|
| 40 |
+
{{- '<｜User｜>' + content + '<｜Assistant｜>'}}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if message['role'] == 'assistant' %}
|
| 44 |
+
{%- if '</think>' in content %}
|
| 45 |
+
{%- set content = (content.split('</think>')|last) %}
|
| 46 |
+
{%- endif %}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
|
| 49 |
+
{%- set ns.is_last_user = false -%}
|
| 50 |
+
{%- if ns.is_tool %}
|
| 51 |
+
{{- '<｜tool▁outputs▁end｜>'}}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set ns.is_first = false %}
|
| 54 |
+
{%- set ns.is_tool = false -%}
|
| 55 |
+
{%- set ns.is_output_first = true %}
|
| 56 |
+
{%- for tool in message['tool_calls'] %}
|
| 57 |
+
{%- set arguments = tool['function']['arguments'] %}
|
| 58 |
+
{%- if arguments is not string %}
|
| 59 |
+
{%- set arguments = arguments|tojson %}
|
| 60 |
+
{%- endif %}
|
| 61 |
+
{%- if not ns.is_first %}
|
| 62 |
+
{%- if content is none %}
|
| 63 |
+
{{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
|
| 64 |
+
}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- set ns.is_first = true -%}
|
| 69 |
+
{%- else %}
|
| 70 |
+
{{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{%- endfor %}
|
| 73 |
+
{{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
|
| 76 |
+
{%- set ns.is_last_user = false -%}
|
| 77 |
+
{%- if ns.is_tool %}
|
| 78 |
+
{{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}
|
| 79 |
+
{%- set ns.is_tool = false -%}
|
| 80 |
+
{%- else %}
|
| 81 |
+
{{- content + '<｜end▁of▁sentence｜>'}}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{%- if message['role'] == 'tool' %}
|
| 85 |
+
{%- set ns.is_last_user = false -%}
|
| 86 |
+
{%- set ns.is_tool = true -%}
|
| 87 |
+
{%- if ns.is_output_first %}
|
| 88 |
+
{{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
|
| 89 |
+
{%- set ns.is_output_first = false %}
|
| 90 |
+
{%- else %}
|
| 91 |
+
{{- '\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
|
| 92 |
+
{%- endif %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{%- endfor -%}
|
| 95 |
+
{%- if ns.is_tool %}
|
| 96 |
+
{{- '<｜tool▁outputs▁end｜>'}}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
|
| 99 |
+
{%- if add_generation_prompt and not ns.is_tool %}
|
| 100 |
+
{{- '<｜Assistant｜>'}}
|
| 101 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"torch_dtype": "float16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12288,
|
| 15 |
+
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 131072,
|
| 54 |
+
"max_window_layers": 36,
|
| 55 |
+
"model_type": "qwen3",
|
| 56 |
+
"num_attention_heads": 32,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"pad_token_id": 151654,
|
| 60 |
+
"quantization_config": {
|
| 61 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 62 |
+
"bnb_4bit_quant_type": "nf4",
|
| 63 |
+
"bnb_4bit_use_double_quant": true,
|
| 64 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 65 |
+
"llm_int8_has_fp16_weight": false,
|
| 66 |
+
"llm_int8_skip_modules": [
|
| 67 |
+
"model.layers.1.self_attn.q_proj",
|
| 68 |
+
"model.layers.1.self_attn.k_proj",
|
| 69 |
+
"model.layers.1.self_attn.v_proj",
|
| 70 |
+
"model.layers.1.self_attn.o_proj",
|
| 71 |
+
"model.layers.2.mlp.gate_proj",
|
| 72 |
+
"model.layers.2.mlp.up_proj",
|
| 73 |
+
"model.layers.2.mlp.down_proj",
|
| 74 |
+
"model.layers.4.mlp.gate_proj",
|
| 75 |
+
"model.layers.4.mlp.up_proj",
|
| 76 |
+
"model.layers.4.mlp.down_proj",
|
| 77 |
+
"model.layers.5.mlp.gate_proj",
|
| 78 |
+
"model.layers.5.mlp.up_proj",
|
| 79 |
+
"model.layers.5.mlp.down_proj",
|
| 80 |
+
"model.layers.6.self_attn.q_proj",
|
| 81 |
+
"model.layers.6.self_attn.k_proj",
|
| 82 |
+
"model.layers.6.self_attn.v_proj",
|
| 83 |
+
"model.layers.6.self_attn.o_proj",
|
| 84 |
+
"model.layers.6.mlp.gate_proj",
|
| 85 |
+
"model.layers.6.mlp.up_proj",
|
| 86 |
+
"model.layers.6.mlp.down_proj",
|
| 87 |
+
"model.layers.33.self_attn.q_proj",
|
| 88 |
+
"model.layers.33.self_attn.k_proj",
|
| 89 |
+
"model.layers.33.self_attn.v_proj",
|
| 90 |
+
"model.layers.33.self_attn.o_proj",
|
| 91 |
+
"model.layers.34.self_attn.q_proj",
|
| 92 |
+
"model.layers.34.self_attn.k_proj",
|
| 93 |
+
"model.layers.34.self_attn.v_proj",
|
| 94 |
+
"model.layers.34.self_attn.o_proj",
|
| 95 |
+
"model.layers.34.mlp.gate_proj",
|
| 96 |
+
"model.layers.34.mlp.up_proj",
|
| 97 |
+
"model.layers.34.mlp.down_proj",
|
| 98 |
+
"lm_head"
|
| 99 |
+
],
|
| 100 |
+
"llm_int8_threshold": 6.0,
|
| 101 |
+
"load_in_4bit": true,
|
| 102 |
+
"load_in_8bit": false,
|
| 103 |
+
"quant_method": "bitsandbytes"
|
| 104 |
+
},
|
| 105 |
+
"rms_norm_eps": 1e-06,
|
| 106 |
+
"rope_scaling": {
|
| 107 |
+
"attn_factor": 0.8782488562869419,
|
| 108 |
+
"factor": 4.0,
|
| 109 |
+
"original_max_position_embeddings": 32768,
|
| 110 |
+
"rope_type": "yarn"
|
| 111 |
+
},
|
| 112 |
+
"rope_theta": 1000000,
|
| 113 |
+
"sliding_window": null,
|
| 114 |
+
"tie_word_embeddings": false,
|
| 115 |
+
"transformers_version": "4.56.2",
|
| 116 |
+
"unsloth_fixed": true,
|
| 117 |
+
"unsloth_version": "2025.10.12",
|
| 118 |
+
"use_cache": true,
|
| 119 |
+
"use_sliding_window": false,
|
| 120 |
+
"vocab_size": 151936
|
| 121 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"max_length": 131072,
|
| 6 |
+
"pad_token_id": 151654,
|
| 7 |
+
"transformers_version": "4.56.2"
|
| 8 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44fa6f482ce7ee78d9f87539909130058e19d6c22f9779fff458ff813ee1f719
|
| 3 |
+
size 4975323439
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:755cfb746ea681550460858235a68dc68c5ecabcb79ab93f4bab632fa3600ee7
|
| 3 |
+
size 2467653345
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|vision_pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd10f523db4ca89f5c99e0fa01276d6dcba9d4e3b1e1dd05216e9296db1f6be2
|
| 3 |
+
size 11423514
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,247 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<|im_start|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<|object_ref_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|object_ref_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<|box_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "<|box_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"151665": {
|
| 183 |
+
"content": "<tool_response>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"151666": {
|
| 191 |
+
"content": "</tool_response>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"151667": {
|
| 199 |
+
"content": "<think>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"151668": {
|
| 207 |
+
"content": "</think>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"151669": {
|
| 215 |
+
"content": "<｜User｜>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": false
|
| 221 |
+
},
|
| 222 |
+
"151670": {
|
| 223 |
+
"content": "<｜Assistant｜>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": false
|
| 229 |
+
}
|
| 230 |
+
},
|
| 231 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 232 |
+
"clean_up_tokenization_spaces": false,
|
| 233 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"legacy": true,
|
| 236 |
+
"max_length": null,
|
| 237 |
+
"model_max_length": 131072,
|
| 238 |
+
"pad_to_multiple_of": null,
|
| 239 |
+
"pad_token": "<|vision_pad|>",
|
| 240 |
+
"pad_token_type_id": 0,
|
| 241 |
+
"padding_side": "right",
|
| 242 |
+
"sp_model_kwargs": {},
|
| 243 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 244 |
+
"unk_token": null,
|
| 245 |
+
"use_default_system_prompt": false,
|
| 246 |
+
"chat_template": "{%- if not add_generation_prompt is defined %}\n {%- set add_generation_prompt = false %}\n{%- endif %}\n{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {%- if ns.is_first_sp %}\n {%- set ns.system_prompt = ns.system_prompt + message['content'] %}\n {%- set ns.is_first_sp = false %}\n {%- else %}\n {%- set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n\n{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}\n{%- if tools is defined and tools is not none %}\n {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\\n' + '```json\\n{\"param1\": \"value1\", \"param2\": \"value2\"}\\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\\n\\n' + 'Make sure the JSON is valid.' + '## Tools\\n\\n### Function\\n\\nYou have the following functions available:\\n\\n') %}\n {%- for tool in tools %}\n {%- set tool_ns.text = tool_ns.text + '\\n```json\\n' + (tool | tojson) + '\\n```\\n' %}\n {%- endfor %}\n {%- if ns.system_prompt|length != 0 %}\n {%- set ns.system_prompt = ns.system_prompt + '\\n\\n' + tool_ns.text %}\n {%- else %}\n {%- set ns.system_prompt = tool_ns.text %}\n {%- endif %}\n{%- endif %}\n{{- bos_token }}\n{{- ns.system_prompt }}\n{%- set last_index = (messages|length - 1) %}\n{%- for message in messages %}\n {%- set content = message['content'] %}\n {%- if message['role'] == 'user' %}\n {%- set ns.is_tool = false -%}\n {%- set ns.is_first = false -%}\n {%- set ns.is_last_user = true -%}\n {%- if loop.index0 == last_index %}\n {{- '<｜User｜>' + content }}\n {%- else %}\n {{- '<｜User｜>' + content + '<｜Assistant｜>'}}\n {%- endif %}\n {%- endif %}\n {%- if message['role'] == 'assistant' %}\n {%- if '</think>' in content %}\n {%- set content = (content.split('</think>')|last) %}\n {%- endif %}\n {%- endif %}\n {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}\n {%- set ns.is_last_user = false -%}\n {%- if ns.is_tool %}\n {{- '<｜tool▁outputs▁end｜>'}}\n {%- endif %}\n {%- set ns.is_first = false %}\n {%- set ns.is_tool = false -%}\n {%- set ns.is_output_first = true %}\n {%- for tool in message['tool_calls'] %}\n {%- set arguments = tool['function']['arguments'] %}\n {%- if arguments is not string %}\n {%- set arguments = arguments|tojson %}\n {%- endif %}\n {%- if not ns.is_first %}\n {%- if content is none %}\n {{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + arguments + '\\n' + '```' + '<｜tool▁call▁end｜>'}}\n }\n {%- else %}\n {{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + arguments + '\\n' + '```' + '<｜tool▁call▁end｜>'}}\n {%- endif %}\n {%- set ns.is_first = true -%}\n {%- else %}\n {{- '\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + arguments + '\\n' + '```' + '<｜tool▁call▁end｜>'}}\n {%- endif %}\n {%- endfor %}\n {{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}\n {%- endif %}\n {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}\n {%- set ns.is_last_user = false -%}\n {%- if ns.is_tool %}\n {{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}\n {%- set ns.is_tool = false -%}\n {%- else %}\n {{- content + '<｜end▁of▁sentence｜>'}}\n {%- endif %}\n {%- endif %}\n {%- if message['role'] == 'tool' %}\n {%- set ns.is_last_user = false -%}\n {%- set ns.is_tool = true -%}\n {%- if ns.is_output_first %}\n {{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}\n {%- set ns.is_output_first = false %}\n {%- else %}\n {{- '\\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}\n {%- endif %}\n {%- endif %}\n{%- endfor -%}\n{%- if ns.is_tool %}\n {{- '<｜tool▁outputs▁end｜>'}}\n{%- endif %}\n{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}\n{%- if add_generation_prompt and not ns.is_tool %}\n {{- '<｜Assistant｜>'}}\n{%- endif %}"
|
| 247 |
+
}
|