Instructions to use lancew/Tongyi-DeepResearch-30B-A3B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lancew/Tongyi-DeepResearch-30B-A3B-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lancew/Tongyi-DeepResearch-30B-A3B-FP8") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lancew/Tongyi-DeepResearch-30B-A3B-FP8") model = AutoModelForCausalLM.from_pretrained("lancew/Tongyi-DeepResearch-30B-A3B-FP8", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lancew/Tongyi-DeepResearch-30B-A3B-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lancew/Tongyi-DeepResearch-30B-A3B-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lancew/Tongyi-DeepResearch-30B-A3B-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lancew/Tongyi-DeepResearch-30B-A3B-FP8
- SGLang
How to use lancew/Tongyi-DeepResearch-30B-A3B-FP8 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "lancew/Tongyi-DeepResearch-30B-A3B-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lancew/Tongyi-DeepResearch-30B-A3B-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "lancew/Tongyi-DeepResearch-30B-A3B-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lancew/Tongyi-DeepResearch-30B-A3B-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lancew/Tongyi-DeepResearch-30B-A3B-FP8 with Docker Model Runner:
docker model run hf.co/lancew/Tongyi-DeepResearch-30B-A3B-FP8
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +89 -0
- config.json +100 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +0 -0
- recipe.yaml +6 -0
- req.py +270 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -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
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- 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>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"decoder_sparse_step": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5472,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"max_window_layers": 28,
|
| 17 |
+
"mlp_only_layers": [],
|
| 18 |
+
"model_type": "qwen3_moe",
|
| 19 |
+
"moe_intermediate_size": 768,
|
| 20 |
+
"norm_topk_prob": true,
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_experts": 128,
|
| 23 |
+
"num_experts_per_tok": 8,
|
| 24 |
+
"num_hidden_layers": 48,
|
| 25 |
+
"num_key_value_heads": 4,
|
| 26 |
+
"output_router_logits": false,
|
| 27 |
+
"pad_token_id": 151643,
|
| 28 |
+
"qkv_bias": false,
|
| 29 |
+
"quantization_config": {
|
| 30 |
+
"activation_scheme": "dynamic",
|
| 31 |
+
"fmt": "e4m3",
|
| 32 |
+
"modules_to_not_convert": [
|
| 33 |
+
"model.layers.0.mlp.gate",
|
| 34 |
+
"model.layers.1.mlp.gate",
|
| 35 |
+
"model.layers.2.mlp.gate",
|
| 36 |
+
"model.layers.3.mlp.gate",
|
| 37 |
+
"model.layers.4.mlp.gate",
|
| 38 |
+
"model.layers.5.mlp.gate",
|
| 39 |
+
"model.layers.6.mlp.gate",
|
| 40 |
+
"model.layers.7.mlp.gate",
|
| 41 |
+
"model.layers.8.mlp.gate",
|
| 42 |
+
"model.layers.9.mlp.gate",
|
| 43 |
+
"model.layers.10.mlp.gate",
|
| 44 |
+
"model.layers.11.mlp.gate",
|
| 45 |
+
"model.layers.12.mlp.gate",
|
| 46 |
+
"model.layers.13.mlp.gate",
|
| 47 |
+
"model.layers.14.mlp.gate",
|
| 48 |
+
"model.layers.15.mlp.gate",
|
| 49 |
+
"model.layers.16.mlp.gate",
|
| 50 |
+
"model.layers.17.mlp.gate",
|
| 51 |
+
"model.layers.18.mlp.gate",
|
| 52 |
+
"model.layers.19.mlp.gate",
|
| 53 |
+
"model.layers.20.mlp.gate",
|
| 54 |
+
"model.layers.21.mlp.gate",
|
| 55 |
+
"model.layers.22.mlp.gate",
|
| 56 |
+
"model.layers.23.mlp.gate",
|
| 57 |
+
"model.layers.24.mlp.gate",
|
| 58 |
+
"model.layers.25.mlp.gate",
|
| 59 |
+
"model.layers.26.mlp.gate",
|
| 60 |
+
"model.layers.27.mlp.gate",
|
| 61 |
+
"model.layers.28.mlp.gate",
|
| 62 |
+
"model.layers.29.mlp.gate",
|
| 63 |
+
"model.layers.30.mlp.gate",
|
| 64 |
+
"model.layers.31.mlp.gate",
|
| 65 |
+
"model.layers.32.mlp.gate",
|
| 66 |
+
"model.layers.33.mlp.gate",
|
| 67 |
+
"model.layers.34.mlp.gate",
|
| 68 |
+
"model.layers.35.mlp.gate",
|
| 69 |
+
"model.layers.36.mlp.gate",
|
| 70 |
+
"model.layers.37.mlp.gate",
|
| 71 |
+
"model.layers.38.mlp.gate",
|
| 72 |
+
"model.layers.39.mlp.gate",
|
| 73 |
+
"model.layers.40.mlp.gate",
|
| 74 |
+
"model.layers.41.mlp.gate",
|
| 75 |
+
"model.layers.42.mlp.gate",
|
| 76 |
+
"model.layers.43.mlp.gate",
|
| 77 |
+
"model.layers.44.mlp.gate",
|
| 78 |
+
"model.layers.45.mlp.gate",
|
| 79 |
+
"model.layers.46.mlp.gate",
|
| 80 |
+
"model.layers.47.mlp.gate",
|
| 81 |
+
"lm_head"
|
| 82 |
+
],
|
| 83 |
+
"quant_method": "fp8",
|
| 84 |
+
"weight_block_size": [
|
| 85 |
+
128,
|
| 86 |
+
128
|
| 87 |
+
]
|
| 88 |
+
},
|
| 89 |
+
"rms_norm_eps": 1e-06,
|
| 90 |
+
"rope_scaling": null,
|
| 91 |
+
"rope_theta": 5000000,
|
| 92 |
+
"router_aux_loss_coef": 0.0,
|
| 93 |
+
"sliding_window": null,
|
| 94 |
+
"tie_word_embeddings": false,
|
| 95 |
+
"transformers_version": "4.57.1",
|
| 96 |
+
"use_cache": true,
|
| 97 |
+
"use_qk_norm": true,
|
| 98 |
+
"use_sliding_window": false,
|
| 99 |
+
"vocab_size": 151936
|
| 100 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.57.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e04a39e64063587239d39672e8e4ee638d145ca7f8e396b6c2114f069133392
|
| 3 |
+
size 4997752648
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b666d582d0d9876e1499eeaf4c6f779e81e28035526bb88eed08a3c3b2103dba
|
| 3 |
+
size 5000546768
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b4bb57ed5132021a4ee8d6444eec6585eab7fd3b48df8c2481ee2bf76b9f137
|
| 3 |
+
size 4999499712
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c3c651b712970251723f0ae37c307e62378757079b2201969132f52a4a98892
|
| 3 |
+
size 4999499728
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09a6b7cd8ddc9f76b13732c5146766178b443e4f3af8d1e27b8569937df15b13
|
| 3 |
+
size 4999499736
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5af5bf8e78110c2fe38adda88be7137aa95b984ad2d6b237cb9a94755982e80b
|
| 3 |
+
size 4999499752
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05a5f685d0f60e406112372d9f62b2eb99138bbbdeaca11ebd68df8c26f746a3
|
| 3 |
+
size 1179294608
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
recipe.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: [lm_head, 're:.*mlp.gate$', 're:.*input_layernorm$', 're:.*post_attention_layernorm$']
|
| 6 |
+
scheme: FP8_BLOCK
|
req.py
ADDED
|
@@ -0,0 +1,270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from openai import OpenAI
|
| 2 |
+
|
| 3 |
+
client = OpenAI(
|
| 4 |
+
base_url="http://127.0.0.1:8010/v1",
|
| 5 |
+
api_key="token-abc123",
|
| 6 |
+
)
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
# question='''
|
| 10 |
+
# 写一首关于春天的诗歌,要求是七言长诗,并给出赏析
|
| 11 |
+
# '''
|
| 12 |
+
question='''
|
| 13 |
+
介绍一下成都
|
| 14 |
+
'''
|
| 15 |
+
|
| 16 |
+
def chat_completion_test(prompt,stream = True):
|
| 17 |
+
messages = [
|
| 18 |
+
{"role": "system", "content": "你是一个专业的AI助手"},
|
| 19 |
+
{"role": "user", "content": prompt}
|
| 20 |
+
]
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
response = client.chat.completions.create(
|
| 24 |
+
model="Tongyi-DeepResearch-30B-A3B-FP8",
|
| 25 |
+
messages=messages,
|
| 26 |
+
max_tokens=4096,
|
| 27 |
+
stream=True,
|
| 28 |
+
temperature=0.7,
|
| 29 |
+
# stream_options={"include_usage": True},
|
| 30 |
+
)
|
| 31 |
+
|
| 32 |
+
if stream:
|
| 33 |
+
for chunk in response:
|
| 34 |
+
if len(chunk.choices):
|
| 35 |
+
delta = chunk.choices[0].delta
|
| 36 |
+
if chunk_content := delta.content:
|
| 37 |
+
print(chunk_content, end="", flush=True)
|
| 38 |
+
if hasattr(delta,"reasoning_content"):
|
| 39 |
+
if chunk_content := delta.reasoning_content:
|
| 40 |
+
print(chunk_content, end="", flush=True)
|
| 41 |
+
else:
|
| 42 |
+
print(response.choices[0].message.content)
|
| 43 |
+
|
| 44 |
+
if __name__ == "__main__":
|
| 45 |
+
|
| 46 |
+
chat_completion_test(question,stream=True)
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
'''
|
| 50 |
+
Tongyi-DeepResearch-30B-A3B-NV
|
| 51 |
+
|
| 52 |
+
<think>
|
| 53 |
+
嗯,用户让我介绍一下成都。首先,我需要确定用户的需求是什么。可能是一个游客想去成都旅游,或者 someone对成都的文化、历史感兴趣。我需要涵盖多个方面,比如地理位置、历史、文化、美食、景点、现代发展等等。
|
| 54 |
+
|
| 55 |
+
首先,成都的基本信息,地理位置在四川盆地西部,四川省的省会,人口大约2100万左右。然后历史方面,成都有4500年的文明史,3000多年的建城史,古蜀国的都城,秦朝建城,三国时期的重要城市,唐朝的繁华,还有抗战时期的陪都,这些历史点都需要提到。
|
| 56 |
+
|
| 57 |
+
接下来是文化部分,大熊猫基地肯定是重点,还有川菜、茶馆文化、方言、休闲生活方式。美食方面,火锅、串串香、担担面、麻婆豆腐这些经典菜肴,以及小吃如钟水饺、龙抄手、赖汤圆、三大炮等。要强调成都作为美食之都的地位。
|
| 58 |
+
|
| 59 |
+
景点方面,武侯祠、杜甫草堂、都江堰、青城山、宽窄巷子、锦里等都是必去的地方。还要提到现代发展,比如新经济城市,科技园区,以及天府国际机场的建设。
|
| 60 |
+
|
| 61 |
+
另外,成都的休闲生活,茶馆文化、夜生活、酒吧区如九眼桥,以及慢节奏的生活方式,这些都是成都独特的魅力所在。可能还需要提到成都的交通便利,比如地铁和机场,方便游客到达。
|
| 62 |
+
|
| 63 |
+
需要注意的是,用户可能对成都的美食特别感兴趣,所以美食部分可以详细一些。同时,大熊猫基地的门票和开放时间可能也是游客关心的,但可能不需要太详细的日期,除非用户进一步询问。另外,现代发展部分可以提到成都的经济地位,作为西部地区的中心,以及近年来的经济增长和科技发展。
|
| 64 |
+
|
| 65 |
+
最后,总结成都的特点,强调其历史与现代的结合,美食与文化的融合。可能需要用友好的语气,让介绍更生动,比如提到“天府之国”、”休闲之都“等称号。要确保信息准确,结构清晰,分点列出,但避免使用Markdown,保持自然的段落分隔。
|
| 66 |
+
|
| 67 |
+
检查是否有遗漏的重要信息,比如天气、最佳旅游时间、交通方式等,但可能用户没有特别提到,所以可以简要带过。或者是否需要提醒游客注意辣椒的量,适应口味,但可能属于旅游贴士,可以放在最后作为建议。
|
| 68 |
+
|
| 69 |
+
总之,需要全面但简洁地介绍成都,涵盖历史、文化、美食、景点、现代发展等方面,让读者对成都有一个全面的了解。
|
| 70 |
+
</think>
|
| 71 |
+
|
| 72 |
+
成都,四川省省会,位于四川盆地西部,是西南地区重要的中心城市,被誉为“天府之国”。这座城市历史悠久、文化底蕴深厚,同时又充满现代活力,是中国西部的经济、文化和交通中心之一。
|
| 73 |
+
|
| 74 |
+
### 一、历史与文化
|
| 75 |
+
- **建城史**:成都拥有超过3000年的建城史,是古蜀文明的发源地之一。早在秦朝时期,成都就成为郡治所在地,三国时期为蜀汉都城。
|
| 76 |
+
- **文化符号**:成都以三国文化(武侯祠)、诗歌文化(杜甫草堂)、道教文化(青城山)和川菜文化闻名,是中华文明的重要组成部分。
|
| 77 |
+
|
| 78 |
+
### 二、美食之都
|
| 79 |
+
成都素有“食在中国,味在四川”之说,川菜是中国八大菜系之一,以“麻辣鲜香”著称:
|
| 80 |
+
- **经典菜肴**:麻婆豆腐、回锅肉、宫保鸡丁、水煮鱼等。
|
| 81 |
+
- **小吃**:钟水饺、龙抄手、赖汤圆、担担面、夫妻肺片、三大炮等。
|
| 82 |
+
- **街巷烟火**:锦里、宽窄巷子、奎星楼街等地汇聚了各类地道小吃,夜市和串串香摊位更是成都夜生活的标志。
|
| 83 |
+
|
| 84 |
+
### 三、自然与生态
|
| 85 |
+
- **大熊猫基地**:���都大熊猫繁育研究基地是全球最大的大熊猫保护机构,游客可近距离观察国宝。
|
| 86 |
+
- **周边自然景观**:都江堰(世界文化遗产,古代水利工程)、青城山(道教名山)、西岭雪山(滑雪胜地)等。
|
| 87 |
+
|
| 88 |
+
### 四、现代都市生活
|
| 89 |
+
- **休闲文化**:成都人以“慢生活”著称,茶馆遍布街头巷尾,麻将文化、川剧变脸、休闲茶楼都是城市特色。
|
| 90 |
+
- **夜生活**:九眼桥酒吧街、船说夜游锦江等场所热闹非凡,年轻人聚集地如太古里、春熙路商圈充满时尚气息。
|
| 91 |
+
- **新经济城市**:成都是中国西部重要的科技、金融和文化创意中心,拥有众多高校和产业园区。
|
| 92 |
+
|
| 93 |
+
### 五、交通与旅游
|
| 94 |
+
- **交通枢纽**:成都双流国际机场和天府国际机场连接全球主要城市,高铁网络通达全国。
|
| 95 |
+
- **必游景点**:武侯祠(三国文化)、杜甫草堂(诗歌文化)、锦里(仿古商业街)、宽窄巷子(老成都记忆)、熊猫基地等。
|
| 96 |
+
|
| 97 |
+
### 六、特色体验
|
| 98 |
+
- **方言与幽默**:成都话幽默风趣,火锅、茶馆、麻将桌上的方言交流是城市独特语言景观。
|
| 99 |
+
- **文创与艺术**:成都的文创产业发达,东郊记忆、蓝顶艺术区、街头涂鸦等展现了年轻与活力。
|
| 100 |
+
- **佛教文化**:文殊院、昭觉寺等古刹香火鼎盛,是心灵静修的好去处。
|
| 101 |
+
|
| 102 |
+
### 七、总结
|
| 103 |
+
成都是一座融合了历史厚重与现代活力的“神仙城市”,既有“窗含西岭千秋雪”的诗意,也有“火锅串串麻辣鲜香”的烟火气。无论是追寻千年古韵,还是感受悠闲生活,成都都能满足你对“慢生活”的向往,同时以其美食、熊猫和创新精神吸引着世界各地的游
|
| 104 |
+
'''
|
| 105 |
+
|
| 106 |
+
'''
|
| 107 |
+
Tongyi-DeepResearch-30B-A3B-FP8-NV
|
| 108 |
+
|
| 109 |
+
<think>
|
| 110 |
+
嗯,用户让我介绍一下成都。首先,我需要确定用户的需求是什么。可能是一个游客想去成都旅游,或者 someone对成都的文化、历史感兴趣,甚至可能是学生做功课需要资料。所以,我需要全面但简洁地覆盖各个方面的信息。
|
| 111 |
+
|
| 112 |
+
首先,成都的基本信息,比如地理位置、气候。然后是历史,成都有悠久的历史,可以提到古蜀文明,比如金沙遗址,还有三国时期的一些故事,比如刘备和武侯祠。经济发展方面,成都作为西南地区的经济中心,高新技术产业和美食文化都很有名,比如熊猫基地和川菜。
|
| 113 |
+
|
| 114 |
+
接下来是文化部分,杜甫草堂、武侯祠这些名胜古迹,还有川剧变脸、蜀锦蜀绣这些非物质文化遗产。美食方面,川菜、火锅、串串香、成都小吃比如担担面、钟水饺,可能还要提到郫县豆瓣酱的作用。
|
| 115 |
+
|
| 116 |
+
交通方面,成都的双流国际机场和天府国际机场,高铁网络发达,地铁系统也很方便。旅游景点除了熊猫基地,还有青城山、都江堰这些自然景观,宽窄巷子、锦里这些历史文化街区。
|
| 117 |
+
|
| 118 |
+
另外,可能还要提到成都的现代发展,比如科技园区,如成都高新区,以及这里的大学,比如四川大学。还有成都的生活节奏,悠闲的生活方式,茶馆文化等等。
|
| 119 |
+
|
| 120 |
+
需要确保信息准确,结构清晰,分点说明会更清楚。可能用户需要的是一个概览,所以每个部分不用太深入,但关键点要覆盖到。另外,语言要口语化,避免使用专业术语过多,让用户容易理解。检查有没有遗漏的重要信息,比如成都的别称“蓉城”,因为市花是芙蓉花。还有可能提到成都的交通便利,比如地铁线路,方便游客出行。
|
| 121 |
+
|
| 122 |
+
最后,总结一下成都的特点,强调其历史、文化和美食的结合,以及现代与传统的融合。这样用户就能有一个全面的了解。可能还要注意时间安排,比如提到最佳旅游时间,气候方面的信息。总之,要确保信息全面、准确、有条理,同时保持简洁易懂。
|
| 123 |
+
</think>
|
| 124 |
+
|
| 125 |
+
成都,简称“蓉”,是四川省省会,位于中国西南地区,是西南地区的科技、商贸、金融中心和交通通信枢纽。以下是对成都的详细介绍:
|
| 126 |
+
|
| 127 |
+
---
|
| 128 |
+
|
| 129 |
+
### **地理与气候**
|
| 130 |
+
- **地理位置**:地处四川盆地西部,东邻重庆,西靠青藏高原,是长江上游的重要城市。
|
| 131 |
+
- **气候类型**:亚热带季风气候,四季分明,气候温和湿润,年平均气温16°C,冬暖夏热,雨量充沛,适合全年旅游。
|
| 132 |
+
|
| 133 |
+
---
|
| 134 |
+
|
| 135 |
+
### **历史与文化**
|
| 136 |
+
- **悠久历史**:作为中国历史文化名城,成都已有约3000年建城史,是古蜀文明的发源地(如金沙遗址、三星堆文化)。
|
| 137 |
+
- **三国文化**:曾是刘备建立蜀汉的都城,武侯祠(中国唯一现存的君臣合祀祠庙)是重要历史遗迹。
|
| 138 |
+
- **文学艺术**:杜甫、李白等文人曾在此留下名篇,锦里、杜甫草堂是文化地标。
|
| 139 |
+
|
| 140 |
+
---
|
| 141 |
+
|
| 142 |
+
### **经济与科技**
|
| 143 |
+
- **经济地位**:西南地区GDP最高的城市,电子信息、装备制造、生物医药等产业发达。
|
| 144 |
+
- **科技园区**:成都高新区(中国西部首个国家自主创新示范区)聚集了大量高科技企业。
|
| 145 |
+
- **交通枢纽**:双流国际机场和天府国际机场(全球最大单体航站楼)、成渝高铁等,通达全国及国际主要城市。
|
| 146 |
+
|
| 147 |
+
---
|
| 148 |
+
|
| 149 |
+
### **美食之都**
|
| 150 |
+
- **川菜发源地**:以“麻、辣、鲜、香”著称,代表菜有麻婆豆腐、回锅肉、水煮鱼等。
|
| 151 |
+
- **小吃与市井文化**:
|
| 152 |
+
- **串串香**:类似火锅的小串食材,价格亲民。
|
| 153 |
+
- **担担面**:细面搭配肉臊、花生碎,麻辣鲜香。
|
| 154 |
+
- **钟水饺**:甜辣口味,皮薄馅嫩。
|
| 155 |
+
- **火锅**:以牛油锅底和鲜切毛肚闻名。
|
| 156 |
+
- **郫县豆瓣酱**:川菜的灵魂调料,起源于成都郫都区。
|
| 157 |
+
|
| 158 |
+
---
|
| 159 |
+
|
| 160 |
+
### **特色景点**
|
| 161 |
+
1. **大熊猫繁育研究基地**:
|
| 162 |
+
- 全球最大的大熊猫保护机构之一,可近距离观察大熊猫及幼崽。
|
| 163 |
+
2. **都江堰与青城山**:
|
| 164 |
+
- **都江堰**:世界文化遗产,古代无坝引水工程奇迹。
|
| 165 |
+
- **青城山**:道教发源地,以“青城天下幽”著称。
|
| 166 |
+
3. **武侯祠与锦里**:
|
| 167 |
+
- **武侯祠**:纪念诸葛亮的祠庙,与汉昭烈庙相邻。
|
| 168 |
+
- **锦里**:仿古商业街,展现三国文化与川西民俗。
|
| 169 |
+
4. **宽窄巷子与锦里**:
|
| 170 |
+
- 宽窄巷子由宽巷子、窄巷子和井巷子组成,融合传统与现代商业。
|
| 171 |
+
- 锦里以三国文化和四川民俗为主题。
|
| 172 |
+
5. **杜甫草堂**:
|
| 173 |
+
- 唐代诗人杜甫流寓成都时的故居,现为纪念馆。
|
| 174 |
+
6. **春熙路与太古里**:
|
| 175 |
+
- 现代商业中心,汇聚奢侈品、潮流品牌和特色餐厅。
|
| 176 |
+
|
| 177 |
+
---
|
| 178 |
+
|
| 179 |
+
### **非物质文化遗产**
|
| 180 |
+
- **川剧变脸**:国家级非物质文化遗产,以瞬间变换脸谱的绝技闻名,可在锦里或专业剧院观赏。
|
| 181 |
+
- **蜀锦蜀绣**:中国传统工艺,蜀锦以色彩绚烂著称,蜀绣细腻生动,成都工艺美术馆可体验制作。
|
| 182 |
+
|
| 183 |
+
---
|
| 184 |
+
|
| 185 |
+
### **生活与休闲**
|
| 186 |
+
- **茶馆文化**:成都人爱饮茶,人民公园鹤鸣茶社、宽窄巷子茶馆是体验市井生活的绝佳去处。
|
| 187 |
+
- **夜生活**:九眼桥酒吧街、玉林路的小酒馆(因赵雷歌曲《成都》走红)充满烟火气。
|
| 188 |
+
|
| 189 |
+
---
|
| 190 |
+
|
| 191 |
+
### **旅行贴士**
|
| 192 |
+
1. **最佳时间**:春秋季(3-5月、9-11月),气候宜人,适合游览。
|
| 193 |
+
2. **交通**:地铁覆盖主要景点,共享单车和出租车便利。
|
| 194 |
+
3. **必尝美食**:除了火锅和小吃,别错过“三大炮”(糯米小吃)和“赖汤圆”。
|
| 195 |
+
|
| 196 |
+
---
|
| 197 |
+
|
| 198 |
+
### **总结**
|
| 199 |
+
成都是一个融合了历史底蕴与现代活力的城市,既有“天府之国”的富庶,也有“休闲之都”的慢生活。无论是探索古蜀文明、品尝麻辣美食,还是与国宝大熊猫亲密接触,这里都能满足多元化的旅行期待
|
| 200 |
+
'''
|
| 201 |
+
|
| 202 |
+
'''
|
| 203 |
+
Tongyi-DeepResearch-30B-A3B-FP8-VACC
|
| 204 |
+
|
| 205 |
+
vllm serve /data/Tongyi-DeepResearch-30B-A3B-FP8/ \
|
| 206 |
+
--trust-remote-code \
|
| 207 |
+
--tensor-parallel-size 2 \
|
| 208 |
+
--max-model-len 65536 \
|
| 209 |
+
--enforce-eager \
|
| 210 |
+
--rope-scaling '{"rope_type":"yarn","factor":2.0,"original_max_position_embeddings":32768}' \
|
| 211 |
+
--port 8010 \
|
| 212 |
+
--served-model-name Tongyi-DeepResearch-30B-A3B-FP8
|
| 213 |
+
|
| 214 |
+
<think>
|
| 215 |
+
嗯,用户让我介绍一下成都。首先,我需要确定用户可能对哪些方面感兴趣。成都作为四川省的省会,有很多不同的特色,比如历史、文化、美食、自然景观等等。我应该全面覆盖这些方面,但也要注意别太啰嗦。
|
| 216 |
+
|
| 217 |
+
用户可能是个游客,想了解旅游景点,或者是个学生做研究,或者单纯对成都感兴趣。我得考虑不同需求,给出有用的信息。比如,旅游的话,推荐景点和美食;历史方面,提一下古蜀文明和三国文化;经济方面,可以提到高新技术产业;还有熊猫基地这样的特色。
|
| 218 |
+
|
| 219 |
+
要注意结构清晰,分点说明可能更易读。比如分历史、文化、美食、景点、现代发展等部分。同时,要加入一些有趣的细节,比如“少不入蜀,老不出川”的说法,或者盖碗茶的文化,这样能让介绍更生动。
|
| 220 |
+
|
| 221 |
+
还要检查有没有遗漏的重要信息,比如杜甫草堂、武侯祠这些历史遗迹,宽窄巷子、锦里这些老街区,还有川菜的代表菜如麻婆豆腐、火锅。另外,熊猫基地是成都的标志性景点,必须提到。
|
| 222 |
+
|
| 223 |
+
用户可能还想知道交通、气候等实用信息,但问题只是“介绍一下”,所以可能不需要太深入,但可以简单提一下。比如成都的交通枢纽地位,地铁覆盖,气候温和湿润。
|
| 224 |
+
|
| 225 |
+
最后,结尾部分可以总结成都的特点,比如慢生活、美食、熊猫,这样用户能记住关键点。保持语气友好,信息准确,避免错误。确保每个部分的信息简洁明了,不过于冗长。
|
| 226 |
+
</think>
|
| 227 |
+
|
| 228 |
+
成都,四川省的省会,位于四川盆地西部,是中国西南地区的重要城市之一,也是国家历史文化名城和新一线城市代表。以下是成都的详细介绍:
|
| 229 |
+
|
| 230 |
+
### 1. **历史与文化**
|
| 231 |
+
- **古蜀文明发源地**:公元前4世纪古蜀国开明王朝迁都于此,命名为“成都”,意为“成都而旺”。
|
| 232 |
+
- **三国文化重镇**:拥有武侯祠(中国唯一纪念诸葛亮和刘备的祠庙)、杜甫草堂等历史遗迹。
|
| 233 |
+
- **文化传承**:川剧、变脸艺术、蜀绣、银花丝等非物质文化遗产丰富,宽窄巷子、锦里等街区保留老成都风貌。
|
| 234 |
+
|
| 235 |
+
### 2. **美食之都**
|
| 236 |
+
- **川菜代表**:以“麻辣”著称,经典菜品包括:
|
| 237 |
+
- **火锅**:麻辣或清油锅底,配毛肚、黄喉等。
|
| 238 |
+
- **麻婆豆腐**:麻、辣、烫、香、酥、嫩兼具。
|
| 239 |
+
- **回锅肉**:豆瓣酱炒制,肥而不腻。
|
| 240 |
+
- **钟水饺**:甜水面搭配红油酱汁。
|
| 241 |
+
- **担担面**:酸辣鲜香,配肉末和芽菜。
|
| 242 |
+
- **街头小吃**:龙抄手、夫妻肺片、酸辣粉、串串香等遍布街头。
|
| 243 |
+
- **茶馆文化**:盖碗茶是标配,人民公园鹤鸣茶社是体验传统茶文化的经典地点。
|
| 244 |
+
|
| 245 |
+
### 3. **自然与生态**
|
| 246 |
+
- **熊猫基地**:全球最大的大熊猫繁育研究基地,可近距离观察国宝。
|
| 247 |
+
- **都江堰-青城山**:世界文化遗产,都江堰是古代水利工程奇迹,青城山为道教发源地。
|
| 248 |
+
- **西岭雪山**:距市区较近的滑雪胜地,冬季热门目的地。
|
| 249 |
+
|
| 250 |
+
### 4. **现代发展**
|
| 251 |
+
- **经济中心**:中国西部科技、金融、商贸和物流枢纽,拥有众多高新技术企业。
|
| 252 |
+
- **交通便利**:双流国际机场和天府国际机场为西南交通核心,地铁网络覆盖广泛。
|
| 253 |
+
- **创意产业**:东郊记忆(工业遗址改造的文化创意园区)、麓湖生态城等地展示城市创新活力。
|
| 254 |
+
|
| 255 |
+
### 5. **休闲与慢生活**
|
| 256 |
+
- **茶馆与麻将**:茶馆遍布全城,麻将文化盛行,体现悠闲生活态度。
|
| 257 |
+
- **夜生活**:九眼桥酒吧街、玉林路等区域夜间热闹,适合体验本地人的社交方式。
|
| 258 |
+
|
| 259 |
+
### 6. **特色活动**
|
| 260 |
+
- **国际赛事**:举办过世界大学生运动会、国际乒联总决赛等。
|
| 261 |
+
- **节庆活动**:正月初一的“逛锦里”、端午节龙舟赛等传统活动热闹非凡。
|
| 262 |
+
|
| 263 |
+
### 7. **实用信息**
|
| 264 |
+
- **气候**:亚热带季风气候,冬无严寒、夏无酷暑,空气湿润。
|
| 265 |
+
- **交通**:地铁覆盖主要景点,公交发达;市内共享单车普及,适合骑行游览。
|
| 266 |
+
|
| 267 |
+
### 总结
|
| 268 |
+
成都融合了古蜀文明、三国历史、现代活力和独特美食,既有武侯祠、杜甫草堂等历史底蕴,也有大熊猫基地、都江堰等自然奇观。这里的生活节奏舒缓,火锅与盖碗茶是城市符号,正因如此,成都被形容为“来了就不想走”的“天府之国”。
|
| 269 |
+
|
| 270 |
+
'''
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 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": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 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 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 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": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|