Instructions to use andrewmonostate/sophia-quotation-v12-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andrewmonostate/sophia-quotation-v12-sft with Transformers:

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

pipe = pipeline("text-generation", model="andrewmonostate/sophia-quotation-v12-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("andrewmonostate/sophia-quotation-v12-sft")
model = AutoModelForMultimodalLM.from_pretrained("andrewmonostate/sophia-quotation-v12-sft")
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]:]))

PEFT
How to use andrewmonostate/sophia-quotation-v12-sft with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use andrewmonostate/sophia-quotation-v12-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andrewmonostate/sophia-quotation-v12-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": "andrewmonostate/sophia-quotation-v12-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/andrewmonostate/sophia-quotation-v12-sft

SGLang

How to use andrewmonostate/sophia-quotation-v12-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 "andrewmonostate/sophia-quotation-v12-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": "andrewmonostate/sophia-quotation-v12-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 "andrewmonostate/sophia-quotation-v12-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": "andrewmonostate/sophia-quotation-v12-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use andrewmonostate/sophia-quotation-v12-sft with Docker Model Runner:
```
docker model run hf.co/andrewmonostate/sophia-quotation-v12-sft
```

sophia-quotation-v12-sft

This model was trained using AITraining.

Training Details

Parameter	Value
Base Model	`Qwen/Qwen3.5-9B`
Trainer	`sft`
Dataset	`monostate/hotel-quotation-syntv4-text`
Epochs	3
Learning Rate	0.0005
Batch Size	1
Block Size	16384
LoRA Rank	32
LoRA Alpha	64
Gradient Accumulation	16

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "PATH_TO_THIS_REPO"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

print(response)

Trained with AITraining

Downloads last month: 2

Safetensors

Model size

9B params

Tensor type

F16

Model tree for andrewmonostate/sophia-quotation-v12-sft

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(374)

this model

andrewmonostate
/

sophia-quotation-v12-sft

sophia-quotation-v12-sft

Training Details

Usage

Model tree for andrewmonostate/sophia-quotation-v12-sft

Dataset used to train andrewmonostate/sophia-quotation-v12-sft