Instructions to use ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18 with Transformers:

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

pipe = pipeline("text-generation", model="ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18")
model = AutoModelForCausalLM.from_pretrained("ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18", 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 ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18

SGLang

How to use ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18 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 "ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18" \
    --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": "ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18",
		"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 "ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18" \
        --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": "ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18 with Docker Model Runner:
```
docker model run hf.co/ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Original model: https://huggingface.co/google/gemma-2-2b-jpn-it

Prompt format

<start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model

Note that this model does not support a System prompt.

Since gemma-2-2b-jpn-it-ablitered-18 is slightly brain damaged compare to the original gemma-2-2b-jpn-it. I decided to try ORPO fine tuning to see if it can be headled.

Using the gemma-2-2b base model, I employed the ORPO method described by mlabonne but the input model was read into VRAM by unsloth to allow using the full 40k dataset to run on a single 3090.

Five epoches was run. Smallest eval_loss was achieve at epoch 7.00. Checkpoint at epoch 7.00 is used to obtain a model adapter and applied it to gemma-2-2b-jpn-it-ablitered-18 to obtain this model.

Epoch	loss	eval_loss	eval_logps/rejected	eval_logps/chosen
1.00	0.9754	1.0344	-1.1506	-0.7516
2.00	0.9629	1.0173	-1.2694	-0.7351
3.00	0.7435	1.0087	-1.4922	-0.7388
4.00	1.0595	1.0026	-1.5920	-0.7310
5.00	1.0525	1.0000	-1.6313	-0.7311
6.00	1.1628	1.0014	-1.7263	-0.7393
7.00	0.8994	0.9971	-1.7264	-0.7324
8.00	0.7448	1.0056	-1.7790	-0.7482
9.00	0.6801	1.0028	-1.7794	-0.7429
10.00	0.9868	1.0069	-1.8065	-0.7505

This model is uploaded here to be evaluated by the Open LLM Leaderboard. Further ORPO fine tuning is currently underway to see if it can regain its sanity. You can play with this model first or wait until I am done with the fine tuning.

Benchmark (100.0*raw scores only)

Click on the model name go to the raw score json generated by Open LLM Leaderboard.

Model	Average	IFEval	BHH	Math Lv5	GPQA	MUSR	MMLU-PRO
gemma-2-2b-jpn-it	30.82	54.11	41.43	0.0	27.52	37.17	24.67
gemma-2-2b-ORPO-jpn-it-abliterated-18 (5 epoches)	29.57	48.05	41.26	0.0	27.18	36.51	24.43
gemma-2-2b-ORPO-jpn-it-abliterated-18 (10 epoches)	TBD	TBD	TBD	TBD	TBD	TBD	TBD
gemma-2-2b-jpn-it-abliterated-17	30.29	52.65	40.46	0.0	27.18	36.90	24.55
gemma-2-2b-jpn-it-abliterated-18	30.61	53.02	40.96	0.0	27.35	37.30	25.05
gemma-2-2b-jpn-it-abliterated-24	30.61	51.37	40.77	0.0	27.77	39.02	24.73

How to run this model

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "gemma-2-2b-ORPO-jpn-it-abliterated-18"
dtype = torch.bfloat16

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda",
    torch_dtype=dtype,)

chat = [
    { "role": "user", "content": "Write a hello world program" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18 --include "*" --local-dir ./

Credits

Thank you mlabonne for describing the ORPO fine tuning method.

Thank you FullOf_Bad_Ideas from LocalLlama for the suggestion of using unsloth to save VRAM.

Downloads last month: 24

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Finetuned

google/gemma-2-2b-jpn-it

Finetuned

(26)

this model

Quantizations

2 models

ymcki
/

gemma-2-2b-ORPO-jpn-it-abliterated-18

Prompt format

Benchmark (100.0*raw scores only)

How to run this model

Downloading using huggingface-cli

Credits

Model tree for ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18

Dataset used to train ymcki/gemma-2-2b-ORPO-jpn-it-abliterated-18