Instructions to use radm/forerunner-qwen7b-orpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use radm/forerunner-qwen7b-orpo with Transformers:

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

pipe = pipeline("text-generation", model="radm/forerunner-qwen7b-orpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("radm/forerunner-qwen7b-orpo")
model = AutoModelForCausalLM.from_pretrained("radm/forerunner-qwen7b-orpo")
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

vLLM

How to use radm/forerunner-qwen7b-orpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "radm/forerunner-qwen7b-orpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "radm/forerunner-qwen7b-orpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/radm/forerunner-qwen7b-orpo

SGLang

How to use radm/forerunner-qwen7b-orpo 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 "radm/forerunner-qwen7b-orpo" \
    --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": "radm/forerunner-qwen7b-orpo",
		"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 "radm/forerunner-qwen7b-orpo" \
        --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": "radm/forerunner-qwen7b-orpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use radm/forerunner-qwen7b-orpo with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for radm/forerunner-qwen7b-orpo to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for radm/forerunner-qwen7b-orpo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for radm/forerunner-qwen7b-orpo to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="radm/forerunner-qwen7b-orpo",
    max_seq_length=2048,
)

Docker Model Runner
How to use radm/forerunner-qwen7b-orpo with Docker Model Runner:
```
docker model run hf.co/radm/forerunner-qwen7b-orpo
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for forerunner-qwen7b-orpo

Model Details

Model Description

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct using the ORPO algorithm with Unsloth for optimization. It has been trained on a custom dataset with a focus on philosophical and esoteric topics. The model is multilingual.

Developed by: radm
Finetuned from model: Qwen/Qwen2.5-7B-Instruct
Model type: Causal LM based on Qwen2 architecture
Language(s): Multilingual
License: Apache 2.0 (inherited from base model)

Uses

Example Output (with temperature=0.6, repetition_penalty=1.15):

User: As a result of what mental process does duality appear in a person?

Model: Dualistic thinking arises from the interaction between an individual and their environment. When a person's consciousness is not yet developed to a certain level, they experience the world through sensory perception. This perception leads to the formation of concepts such as "good" and "bad," "right" and "wrong." These oppositions manifest themselves in actions or emotions, leading to dualism. The mind then begins to differentiate between these opposites, creating a division into two parts: one that experiences and another that observes this experience. This observation is necessary for the development of language and thought processes, which are based on distinguishing and naming objects according to their properties. As a result, the mind learns to distinguish between things, people, events, and their qualities, forming a complex system of relationships. This process is similar to how a child learns to recognize and name objects around them. However, it's important to note that the duality formed within the mind does not necessarily reflect external reality but rather is a product of internal cognitive processes.

Out-of-Scope Use

The model is not designed for generating harmful, unethical, biased, or factually incorrect content. Performance on tasks outside its training domain (philosophical/esoteric chat) may be suboptimal.

Bias, Risks, and Limitations

The model inherits biases from its base model (Qwen/Qwen2.5-7B-Instruct) and the fine-tuning dataset. It may generate plausible-sounding but incorrect or nonsensical information, especially on complex topics. Its understanding is based on patterns in the data, not genuine comprehension or consciousness. Use the outputs with critical judgment.

Training Details

Training Data

The model was fine-tuned using the ORPO algorithm on a custom dataset. This dataset contains pairs of preferred and rejected responses for given prompts, focusing on philosophical and esoteric themes. A small validation split (0.5%) was used.

Training Procedure

The training was performed using the Unsloth library integrated with trl's ORPOTrainer.

Training Hyperparameters

Framework: Unsloth + ORPO
Base Model: Qwen/Qwen2.5-7B-Instruct
LoRA Configuration:
- r: 64
- lora_alpha: 64
- lora_dropout: 0.0
- bias: "none"
- target_modules: ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]
- use_rslora: True
Precision: bfloat16 mixed precision
Quantization: Loaded in 4-bit
Optimizer: Paged AdamW 8-bit
Learning Rate: 1e-5
LR Scheduler: Cosine
Warmup Steps: 8
Batch Size (per device): 1
Gradient Accumulation Steps: 32 (Effective Batch Size: 32)
Max Sequence Length: 3072
Epochs: 1
ORPO Beta: 0.1