Instructions to use SlowGuess/ABForge-Qwen3-8B-Combined-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SlowGuess/ABForge-Qwen3-8B-Combined-SFT with Transformers:

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

pipe = pipeline("text-generation", model="SlowGuess/ABForge-Qwen3-8B-Combined-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SlowGuess/ABForge-Qwen3-8B-Combined-SFT")
model = AutoModelForCausalLM.from_pretrained("SlowGuess/ABForge-Qwen3-8B-Combined-SFT", device_map="auto")
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 SlowGuess/ABForge-Qwen3-8B-Combined-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SlowGuess/ABForge-Qwen3-8B-Combined-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": "SlowGuess/ABForge-Qwen3-8B-Combined-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SlowGuess/ABForge-Qwen3-8B-Combined-SFT

SGLang

How to use SlowGuess/ABForge-Qwen3-8B-Combined-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 "SlowGuess/ABForge-Qwen3-8B-Combined-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": "SlowGuess/ABForge-Qwen3-8B-Combined-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 "SlowGuess/ABForge-Qwen3-8B-Combined-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": "SlowGuess/ABForge-Qwen3-8B-Combined-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SlowGuess/ABForge-Qwen3-8B-Combined-SFT with Docker Model Runner:
```
docker model run hf.co/SlowGuess/ABForge-Qwen3-8B-Combined-SFT
```

ABForge-Qwen3-8B-Combined-SFT

The SFT-only stage of the unified ABForge model: Qwen/Qwen3-8B supervised fine-tuned for one full epoch (step 602) on a 1:1 mixture of both ABForge tasks, before any RL. This is the initialization for SlowGuess/ABForge-Qwen3-8B-Combined, and the "SFT only" row of the paper's post-training ablation.

Tasks

Both ABForge tasks in one checkpoint — Task 1: Ablation Objective Generation (propose Target Module / Research Question pairs for a paper) and Task 2: Ablation Experiment Design (produce an executable ablation plan).

Training data

Mixed-task SFT on train/sft_task1_45961.jsonl + train/sft_task2_37019.jsonl from SlowGuess/abforge-data (derived from CC-licensed research papers), shuffled 1:1, one full epoch.

Results

Full AblationBench, automated rubric-based LLM-as-a-Judge evaluation:

Stage	Task 1 (%)	Task 2 (%)
`Qwen/Qwen3-8B` (base)	44.4	43.4
This model (unified, SFT only)	30.7	52.2
`-Combined` (unified, SFT → GRPO)	55.9	62.4

SFT alone improves Task 2 but degrades Task 1 relative to the base model; it serves as an effective initialization for the subsequent joint RL stage rather than as a final model.

Related models

SlowGuess/ABForge-Qwen3-8B-Combined — the released unified model
SlowGuess/ABForge-Qwen3-8B-Task1-SFT / -Task2-SFT — task-specific SFT counterparts

Evaluation

Reproduce AblationBench evaluation with the SlowGuess/Abforge_1 code.

Downloads last month: 21

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for SlowGuess/ABForge-Qwen3-8B-Combined-SFT

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(1997)

this model