Instructions to use ptkag1712/rapp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ptkag1712/rapp with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B-Base")
model = PeftModel.from_pretrained(base_model, "ptkag1712/rapp")

Transformers

How to use ptkag1712/rapp with Transformers:

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

pipe = pipeline("text-generation", model="ptkag1712/rapp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ptkag1712/rapp", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ptkag1712/rapp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ptkag1712/rapp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ptkag1712/rapp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ptkag1712/rapp

SGLang

How to use ptkag1712/rapp 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 "ptkag1712/rapp" \
    --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": "ptkag1712/rapp",
		"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 "ptkag1712/rapp" \
        --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": "ptkag1712/rapp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use ptkag1712/rapp with Docker Model Runner:
```
docker model run hf.co/ptkag1712/rapp
```

ptkag1712 commited on May 2

Commit

a349c0b

verified ·

1 Parent(s): 8e867fc

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
chat_template.jinja +1 -1
tokenizer.json +2 -2

adapter_config.json CHANGED Viewed

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
     "k_proj",
     "o_proj",
-    "gate_proj",
-    "down_proj",
-    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "gate_proj",
     "k_proj",
     "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f17b01037c47e623f10a960193c9b1afb3d4ee22bf5fc3e0ab98d324fe8c69a
 size 264308896

 version https://git-lfs.github.com/spec/v1
+oid sha256:e779f1aad484ffce7cd4311110fa84d23caf80621cc04de1a5d69f2e6757f735
 size 264308896

chat_template.jinja CHANGED Viewed

@@ -1,4 +1,4 @@
 {% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + eos_token }}{% set loop_messages = messages[1:] %}{% else %}{{ 'You are an AI assistant that analyzes text to choose suitable actions.
 Given an input text, think step-by-step to identify which actions is needed to protect user information in given text.
 Provide your reasoning process within <start_working_out> and <end_working_out>.
-Then, provide the appropriate action to protect given text (e.g., masking, generalizing, shuffling, no action needed) within <SOLUTION></SOLUTION>.' + eos_token }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ message['content'] }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_working_out>' }}{% endif %}

 {% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + eos_token }}{% set loop_messages = messages[1:] %}{% else %}{{ 'You are an AI assistant that analyzes text to choose suitable actions.
 Given an input text, think step-by-step to identify which actions is needed to protect user information in given text.
 Provide your reasoning process within <start_working_out> and <end_working_out>.
+Then, provide the appropriate one or multiple actions (divide by commas) to protect given text (e.g., masking, generalizing, shuffling, no action needed) within <SOLUTION></SOLUTION>.' + eos_token }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ message['content'] }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_working_out>' }}{% endif %}

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c7decfce2fc1ca1ab4645fe7b73f15fcf500c30cb66dd7943ea7d481a07b30
-size 11423011

 version https://git-lfs.github.com/spec/v1
+oid sha256:10ba4ba91270b1a50e5cd8e51023bccc66fc4ac4909dd7ae7ab29433411c9bb9
+size 11422844