Instructions to use Questionmarkboy/frankenstein-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Questionmarkboy/frankenstein-2.0 with Transformers:

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

pipe = pipeline("text-generation", model="Questionmarkboy/frankenstein-2.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Questionmarkboy/frankenstein-2.0")
model = AutoModelForCausalLM.from_pretrained("Questionmarkboy/frankenstein-2.0", 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 Questionmarkboy/frankenstein-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Questionmarkboy/frankenstein-2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Questionmarkboy/frankenstein-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Questionmarkboy/frankenstein-2.0

SGLang

How to use Questionmarkboy/frankenstein-2.0 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 "Questionmarkboy/frankenstein-2.0" \
    --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": "Questionmarkboy/frankenstein-2.0",
		"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 "Questionmarkboy/frankenstein-2.0" \
        --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": "Questionmarkboy/frankenstein-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Questionmarkboy/frankenstein-2.0 with Docker Model Runner:
```
docker model run hf.co/Questionmarkboy/frankenstein-2.0
```

Questionmarkboy commited on 17 days ago

Commit

3c8fdc7

verified ·

1 Parent(s): 0421678

Create README.md

Browse files

Files changed (1) hide show

README.md +91 -0

README.md ADDED Viewed

	@@ -0,0 +1,91 @@

+---
+license: apache-2.0
+tags:
+  - mistral
+  - merge
+  - lora
+  - fine-tuned
+  - qlora
+  - chat
+  - reasoning
+base_model:
+  - HuggingFaceH4/zephyr-7b-beta
+  - teknium/OpenHermes-2.5-Mistral-7B
+  - cognitivecomputations/Dolphin-2.6-mistral-7b-dpo
+---
+# 🧟 Frankenstein 2.0
+A custom AI assistant stitched together from three Mistral-7B models,
+then fine-tuned — built entirely on Kaggle.
+## 🧬 What Is This?
+Frankenstein 2.0 is a **merged model** combining the strengths of three
+open-source models, then fine-tuned with QLoRA on coding + general
+instruction data.
+| Component | Contribution |
+|---|---|
+| Zephyr-7B-beta | Instruction following + structure |
+| OpenHermes-2.5 | Warmth + conversational tone |
+| Dolphin-2.6-dpo | Obedience + helpfulness |
+## 🎓 Training Details
+- **Base:** Merge of 3× Mistral-7B variants
+- **Fine-tuning:** QLoRA (4-bit NF4)
+- **LoRA:** rank 16, alpha 32
+- **Data:** 3000 general + 3000 coding examples
+- **Hardware:** 2× NVIDIA Tesla T4 (Kaggle)
+## 💡 Capabilities
+✅ Python coding & debugging
+✅ Explaining complex topics simply
+✅ Step-by-step reasoning (with `<think>` tags)
+✅ Document Q&A (RAG-ready)
+✅ Tool use (web search, calculator)
+## 🚀 How To Use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+model = AutoModelForCausalLM.from_pretrained(
+    "Questionmarkboy/frankenstein-2.0",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Questionmarkboy/frankenstein-2.0")
+messages = [{"role": "user", "content": "Explain blockchain to a 10-year-old"}]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True,
+    return_tensors="pt").to(model.device)
+output = model.generate(inputs, max_new_tokens=200)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+## ⚠️ Limitations
+- 7B model — may struggle with very long code generation (e.g. full HTML apps)
+- Knowledge limited to training data
+- Best for English tasks
+## 🙏 Credits
+- Base models by [HuggingFaceH4](https://huggingface.co/HuggingFaceH4),
+  [Teknium](https://huggingface.co/teknium), and
+  [Cognitive Computations](https://huggingface.co/cognitivecomputations)
+- Built with Kaggle
+## 📜 License
+Apache 2.0 (inherited from Mistral base). Please credit the original
+base models when using this.
+---
+*It's alive! 🧟⚡*