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

Libraries

How to use matverest/FINAL with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("matverest/FINAL")
model = AutoModelForCausalLM.from_pretrained("matverest/FINAL")
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 Settings

vLLM

How to use matverest/FINAL with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/matverest/FINAL

SGLang

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

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

matverest commited on Jun 10, 2025

Commit

ba62d85

verified ·

1 Parent(s): 00b5ff3

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +5 -7

chat_template.jinja CHANGED Viewed

@@ -1,11 +1,9 @@
-{%- set sys =
-   "You are an expert in advanced master-level STEM multiple-choice questions.\n"
-   ~ "When given a question with choices A through D:\n"
-   ~ "1. Do NOT output any chain-of-thought or explanation.\n"
-   ~ "2. ONLY output exactly one of these four tokens (including the leading space): \" A\", \" B\", \" C\", or \" D\".\n"
-   ~ "3. Do not add any punctuation or extra text before or after."
 -%}
-{%- set usr = messages[0].content | replace('Answer:', '') -%}
 {{- "<|im_start|>system\n" ~ sys ~ "\n<|im_end|>\n" -}}
 {{- "<|im_start|>user\n"  ~ usr ~ "\n<|im_end|>\n" -}}
 {{- "<|im_start|>assistant\n""\nAnswer:" -}}

+{%- set sys =
+   "You are an expert in STEM multiple-choice questions.\n"
+   ~ "Pick the correct option: A, B, C, D.\n"
+   ~ "After \"Answer:\" reply directly with that single token.\n"
 -%}
+{%- set usr = messages[0].content | replace('Answer:', 'Pick the letter of the correct option (A, B, C, D)') -%}
 {{- "<|im_start|>system\n" ~ sys ~ "\n<|im_end|>\n" -}}
 {{- "<|im_start|>user\n"  ~ usr ~ "\n<|im_end|>\n" -}}
 {{- "<|im_start|>assistant\n""\nAnswer:" -}}