Instructions to use cs-552-2026-catma/general_knowledge_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-catma/general_knowledge_model with Transformers:

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

pipe = pipeline("text-generation", model="cs-552-2026-catma/general_knowledge_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-catma/general_knowledge_model")
model = AutoModelForMultimodalLM.from_pretrained("cs-552-2026-catma/general_knowledge_model")
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 cs-552-2026-catma/general_knowledge_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs-552-2026-catma/general_knowledge_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs-552-2026-catma/general_knowledge_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-catma/general_knowledge_model

SGLang

How to use cs-552-2026-catma/general_knowledge_model 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 "cs-552-2026-catma/general_knowledge_model" \
    --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": "cs-552-2026-catma/general_knowledge_model",
		"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 "cs-552-2026-catma/general_knowledge_model" \
        --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": "cs-552-2026-catma/general_knowledge_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-catma/general_knowledge_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-catma/general_knowledge_model
```

General Knowledge Model

This model is the General Knowledge individual-model submission for the CS-552 Modern NLP course project. It is a merged post-trained checkpoint based on Qwen/Qwen3-1.7B, developed by Tuan Dang Nguyen for closed-book multiple-choice general knowledge evaluation.

The uploaded checkpoint corresponds to the final Stage 5 merge-aware DPO model:

sft_dpo_stage5_error_contrastive_mergeaware_v1_r16_lr8e8_beta003_eval100_500_merged

Task And Output Format

The model receives a multiple-choice question and should answer with exactly one option letter inside a LaTeX boxed expression:

\boxed{C}

The evaluation pipeline extracts the letter inside \boxed{...}. Any surrounding reasoning is ignored for scoring, but the intended behavior is a concise boxed final answer.

Training Summary

The training campaign used LoRA-based post-training on top of Qwen/Qwen3-1.7B.

Main stages:

Supervised fine-tuning on mixed general-knowledge multiple-choice data.
Hard-source and CI-style refinements, including MMLU-Pro and variable option-count examples.
Plus Quartz v1 SFT, which first reached the best hidden-CI score.
Conservative Stage 2 SFT refinement from the Plus Quartz anchor.
Stage 5 merge-aware DPO using the Stage 2 model's own wrong boxed answers plus protection pairs.

The final Stage 5 model is selected because it is the strongest merged local checkpoint. The strongest hidden-CI score was first reached by the Plus Quartz SFT anchor, and the later Stage 2/DPO submissions tied that hidden score.

Evaluation

Local evaluation used the course ten-example public General Knowledge validation snapshot in both prompt modes plus a 290-example diagnostic set built from public multiple-choice sources.

Model	Role	Local diagnostic	Public 10-example validation	Extraction	Hidden CI
`sft_plus_quartz_v1_r128_7200_merged`	First hidden-CI anchor	247/290	7/10 in both prompt modes	100%	0.4900
`sft_stage2_plus_quartz_v1_r32_lr5e7_800_merged`	Best retained SFT refinement	248/290	7/10 in both prompt modes	100%	0.4900 tie
`sft_dpo_stage2_plus_quartz_v1_from_800_mistake_only_r16_lr2e7_beta005_200_merged`	Early DPO refinement	248/290	7/10 in both prompt modes	100%	0.4900 tie
`sft_dpo_stage5_error_contrastive_mergeaware_v1_r16_lr8e8_beta003_eval100_500_merged`	Uploaded final model	249/290	7/10 in both prompt modes	100%	0.4900 tie

Interpretation: DPO improved the retained merged local diagnostic result and made checkpoint selection more robust, but it did not improve beyond the best hidden-CI SFT score of 0.4900.

Usage Notes

This checkpoint is a fully merged model, not a standalone LoRA adapter. It can be loaded with standard transformers text-generation tooling.

For best compatibility with the course evaluator:

Ask closed-book multiple-choice questions.
Include clear answer options.
Require the model to finish with \boxed{LETTER}.
Score only the extracted boxed letter.

Example prompt:

Answer the following multiple-choice question. Return only the final answer in the form \boxed{LETTER}.

Question: Which planet is known as the Red Planet?
A) Venus
B) Mars
C) Jupiter
D) Mercury

Expected style:

\boxed{B}

Limitations

This model is specialized for English closed-book multiple-choice general knowledge. It is not a general chat assistant and should not be used as a reliable factual oracle outside the benchmark setting. Local diagnostics were useful for model selection but did not perfectly predict hidden-CI changes; hidden-CI accuracy remained tied at 0.4900 for the final refinements.

Downloads last month: 916

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for cs-552-2026-catma/general_knowledge_model

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(524)

this model

cs-552-2026-catma
/

general_knowledge_model