Text Generation
Transformers
Safetensors
Chinese
English
deepseek_v3
vLLM
GPTQ
conversational
custom_code
text-generation-inference
4-bit precision
awq
Instructions to use QuantTrio/DeepSeek-V3.1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuantTrio/DeepSeek-V3.1-AWQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="QuantTrio/DeepSeek-V3.1-AWQ", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("QuantTrio/DeepSeek-V3.1-AWQ", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("QuantTrio/DeepSeek-V3.1-AWQ", trust_remote_code=True) 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use QuantTrio/DeepSeek-V3.1-AWQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuantTrio/DeepSeek-V3.1-AWQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuantTrio/DeepSeek-V3.1-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/QuantTrio/DeepSeek-V3.1-AWQ
- SGLang
How to use QuantTrio/DeepSeek-V3.1-AWQ 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 "QuantTrio/DeepSeek-V3.1-AWQ" \ --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": "QuantTrio/DeepSeek-V3.1-AWQ", "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 "QuantTrio/DeepSeek-V3.1-AWQ" \ --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": "QuantTrio/DeepSeek-V3.1-AWQ", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use QuantTrio/DeepSeek-V3.1-AWQ with Docker Model Runner:
docker model run hf.co/QuantTrio/DeepSeek-V3.1-AWQ
Commit ·
0fdeb8b
1
Parent(s): 4e7ab3e
Fix chat_template crash when assistant message omits the `content` key (#5)
Browse files- Fix chat_template crash when assistant message omits the `content` key (4990745e8bd45991d7f466a1e8efa4bc62d8e837)
Co-authored-by: Quentin Gallouédec <qgallouedec@users.noreply.huggingface.co>
- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -31,5 +31,5 @@
|
|
| 31 |
"sp_model_kwargs": {},
|
| 32 |
"unk_token": null,
|
| 33 |
"tokenizer_class": "LlamaTokenizerFast",
|
| 34 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not thinking is defined %}{% set thinking = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- if ns.is_last_user %}{{'<|Assistant|></think>'}}{%- endif %}{%- set ns.is_last_user = false -%}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message
|
| 35 |
}
|
|
|
|
| 31 |
"sp_model_kwargs": {},
|
| 32 |
"unk_token": null,
|
| 33 |
"tokenizer_class": "LlamaTokenizerFast",
|
| 34 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not thinking is defined %}{% set thinking = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- if ns.is_last_user %}{{'<|Assistant|></think>'}}{%- endif %}{%- set ns.is_last_user = false -%}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message.get('content') is none %}{{'<|tool▁calls▁begin|><|tool▁call▁begin|>'+ tool['function']['name'] + '<|tool▁sep|>' + tool['function']['arguments'] + '<|tool▁call▁end|>'}}{%- else %}{{message['content'] + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['function']['name'] + '<|tool▁sep|>' + tool['function']['arguments'] + '<|tool▁call▁end|>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'<|tool▁call▁begin|>'+ tool['function']['name'] + '<|tool▁sep|>' + tool['function']['arguments'] + '<|tool▁call▁end|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}{%- if ns.is_last_user %}{{'<|Assistant|>'}}{%- if message['prefix'] is defined and message['prefix'] and thinking %}{{'<think>'}} {%- else %}{{'</think>'}}{%- endif %}{%- endif %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{%- set content = message['content'] -%}{%- if '</think>' in content %}{%- set content = content.split('</think>', 1)[1] -%}{%- endif %}{{content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{{'<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endfor -%}{%- if add_generation_prompt and ns.is_last_user and not ns.is_tool %}{{'<|Assistant|>'}}{%- if not thinking %}{{'</think>'}}{%- else %}{{'<think>'}}{%- endif %}{% endif %}"
|
| 35 |
}
|