Instructions to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="ericflo/Qwen2.5-7B-Think-KTO-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ericflo/Qwen2.5-7B-Think-KTO-v0.1")
model = AutoModelForCausalLM.from_pretrained("ericflo/Qwen2.5-7B-Think-KTO-v0.1")
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]:]))

llama-cpp-python

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ericflo/Qwen2.5-7B-Think-KTO-v0.1",
	filename="Qwen2.5-7B-Think-KTO-v0.1-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Use Docker

docker model run hf.co/ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

LM Studio
Jan

vLLM

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ericflo/Qwen2.5-7B-Think-KTO-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ericflo/Qwen2.5-7B-Think-KTO-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

SGLang

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 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 "ericflo/Qwen2.5-7B-Think-KTO-v0.1" \
    --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": "ericflo/Qwen2.5-7B-Think-KTO-v0.1",
		"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 "ericflo/Qwen2.5-7B-Think-KTO-v0.1" \
        --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": "ericflo/Qwen2.5-7B-Think-KTO-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with Ollama:
```
ollama run hf.co/ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M
```

Unsloth Studio

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 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 ericflo/Qwen2.5-7B-Think-KTO-v0.1 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 ericflo/Qwen2.5-7B-Think-KTO-v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ericflo/Qwen2.5-7B-Think-KTO-v0.1 to start chatting

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with Docker Model Runner:
```
docker model run hf.co/ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M
```

Lemonade

How to use ericflo/Qwen2.5-7B-Think-KTO-v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ericflo/Qwen2.5-7B-Think-KTO-v0.1:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-7B-Think-KTO-v0.1-Q4_K_M

List all available models

lemonade list

Qwen2.5-Think-KTO v0.1: A Reasoning-Enhanced Language Model

NOTE: This model is currently undertrained and needs some coaxing to output <think>...</think> tags.

What's New in v0.1

This initial release enhances the base Qwen2.5-7B model's reasoning capabilities using Kahneman-Tversky Optimization (KTO). The model is trained using binary feedback signals, indicating whether outputs are desirable or undesirable for given inputs.

How It Works

The model generates responses using a simple thought-then-answer format:

<think>
Let me approach this step by step...
First, we need to consider X...
Then, looking at Y...
Finally, Z leads us to...
</think>

[final answer based on thought process]

Technical Details

Base Architecture

Base Model: Qwen2.5-7B
Training Approach: Kahneman-Tversky Optimization (KTO)
Dataset: Binary feedback signals (desirable/undesirable outputs)
Quality Control: Programmatic validation

Training Parameters

Optimization:
- Learning Rate: 5e-6
- Scheduler: Cosine with 0.1 warmup ratio
- Optimizer: AdamW 8-bit
- Batch Size: 5 per device
- Gradient Accumulation Steps: 1
- Number of Epochs: 3
Model Config:
- Max Length: 3746
- Max Prompt Length: 364
- Attention Implementation: Flash Attention 2
- Gradient Checkpointing: Enabled
Infrastructure:
- Accelerate for distributed training
- Wandb logging
- LIGER optimization enabled

What's It Good For?

✅ Tasks requiring natural thought processes ✅ Scenarios where binary feedback is available ✅ Problems benefiting from human-like reasoning ✅ Applications needing clear thought-to-answer progression

Limitations

Bounded by base Qwen2.5-7B capabilities
May not generalize beyond training distribution
First version with room for improvement
Performance on non-reasoning tasks unchanged
Limited by quality of binary feedback

Example Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ericflo/Qwen2.5-Think-KTO-v0.1")
tokenizer = AutoTokenizer.from_pretrained("ericflo/Qwen2.5-Think-KTO-v0.1")

prompt = "What are the implications of Moore's Law slowing down?"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
output = model.generate(input_ids, max_length=512)
response = tokenizer.decode(output[0])

Citation

@misc{qwen25-think-kto,
  title={Qwen2.5-Think-KTO: Enhanced Reasoning Through Human-Aware Learning},
  author={[Eric Florenzano]},
  year={2024},
  howpublished={\url{https://huggingface.co/ericflo/Qwen2.5-Think-KTO-v0.1}}
}

Acknowledgments

This model builds on the Qwen2.5-7B base model and implements the KTO approach developed by Ethayarajh et al. Special thanks to the authors of the KTO paper and the broader AI research community for their contributions to model alignment techniques.

Downloads last month: 58

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for ericflo/Qwen2.5-7B-Think-KTO-v0.1

Base model

Qwen/Qwen2.5-7B

Quantized

(82)

this model

Quantizations

1 model

ericflo
/

Qwen2.5-7B-Think-KTO-v0.1