Text Generation
Safetensors
Chinese
English
minicpm3
conversational
custom_code
4-bit precision
gptq
Instructions to use openbmb/MiniCPM3-4B-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use openbmb/MiniCPM3-4B-GPTQ-Int4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/MiniCPM3-4B-GPTQ-Int4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openbmb/MiniCPM3-4B-GPTQ-Int4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/openbmb/MiniCPM3-4B-GPTQ-Int4
- SGLang
How to use openbmb/MiniCPM3-4B-GPTQ-Int4 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 "openbmb/MiniCPM3-4B-GPTQ-Int4" \ --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": "openbmb/MiniCPM3-4B-GPTQ-Int4", "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 "openbmb/MiniCPM3-4B-GPTQ-Int4" \ --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": "openbmb/MiniCPM3-4B-GPTQ-Int4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use openbmb/MiniCPM3-4B-GPTQ-Int4 with Docker Model Runner:
docker model run hf.co/openbmb/MiniCPM3-4B-GPTQ-Int4
Update tokenizer_config.json
Browse files- tokenizer_config.json +4 -2
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -110,7 +112,7 @@
|
|
| 110 |
"pad_token": null,
|
| 111 |
"sp_model_kwargs": {},
|
| 112 |
"spaces_between_special_tokens": false,
|
| 113 |
-
"tokenizer_class": "
|
| 114 |
"unk_token": "<unk>",
|
| 115 |
"use_default_system_prompt": false,
|
| 116 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": ["tokenization_minicpm.MiniCPMTokenizer", null]
|
| 4 |
+
},
|
| 5 |
"add_bos_token": true,
|
| 6 |
"add_eos_token": false,
|
|
|
|
| 7 |
"added_tokens_decoder": {
|
| 8 |
"0": {
|
| 9 |
"content": "<unk>",
|
|
|
|
| 112 |
"pad_token": null,
|
| 113 |
"sp_model_kwargs": {},
|
| 114 |
"spaces_between_special_tokens": false,
|
| 115 |
+
"tokenizer_class": "MiniCPMTokenizer",
|
| 116 |
"unk_token": "<unk>",
|
| 117 |
"use_default_system_prompt": false,
|
| 118 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|