Instructions to use RomilY/PCaPLMM_SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RomilY/PCaPLMM_SFT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RomilY/PCaPLMM_SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RomilY/PCaPLMM_SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RomilY/PCaPLMM_SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RomilY/PCaPLMM_SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RomilY/PCaPLMM_SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RomilY/PCaPLMM_SFT

SGLang

How to use RomilY/PCaPLMM_SFT 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 "RomilY/PCaPLMM_SFT" \
    --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": "RomilY/PCaPLMM_SFT",
		"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 "RomilY/PCaPLMM_SFT" \
        --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": "RomilY/PCaPLMM_SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RomilY/PCaPLMM_SFT with Docker Model Runner:
```
docker model run hf.co/RomilY/PCaPLMM_SFT
```

PCaPLMM_SFT / tokenizer_config.json

RomilY

Upload folder using huggingface_hub

d0a810b 11 months ago

Raw

History Blame Contribute Delete

1.58 kB

	{
	"add_bos_token": false,
	"add_eos_token": false,
	"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
	}
	},
	"auto_map": {
	"AutoTokenizer": [
	"tokenization_baichuan.BaichuanTokenizer",
	null
	]
	},
	"bos_token": "<s>",
	"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '</s>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '</s>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n' }}{% endif %}{% endfor %}",
	"clean_up_tokenization_spaces": false,
	"eos_token": "</s>",
	"extra_special_tokens": {},
	"model_max_length": 4096,
	"pad_token": "<unk>",
	"padding_side": "left",
	"sp_model_kwargs": {},
	"split_special_tokens": false,
	"tokenizer_class": "BaichuanTokenizer",
	"unk_token": "<unk>",
	"use_fast": false
	}