Instructions to use jz666/simpo-train-large-wrong with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jz666/simpo-train-large-wrong with Transformers:

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

pipe = pipeline("text-generation", model="jz666/simpo-train-large-wrong")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jz666/simpo-train-large-wrong")
model = AutoModelForCausalLM.from_pretrained("jz666/simpo-train-large-wrong")
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 jz666/simpo-train-large-wrong with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jz666/simpo-train-large-wrong"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jz666/simpo-train-large-wrong",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jz666/simpo-train-large-wrong

SGLang

How to use jz666/simpo-train-large-wrong 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 "jz666/simpo-train-large-wrong" \
    --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": "jz666/simpo-train-large-wrong",
		"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 "jz666/simpo-train-large-wrong" \
        --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": "jz666/simpo-train-large-wrong",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jz666/simpo-train-large-wrong with Docker Model Runner:
```
docker model run hf.co/jz666/simpo-train-large-wrong
```

simpo-train-large-wrong

This model is a fine-tuned version of google/gemma-2-9b-it on the jz666/gemma2-ultrafeedback-ppl-split dataset. It achieves the following results on the evaluation set:

Loss: 4.5115
Rewards/chosen: -5.4495
Rewards/rejected: -6.3534
Rewards/accuracies: 0.5963
Rewards/margins: 0.9039
Logps/rejected: -0.6353
Logps/chosen: -0.5450
Logits/rejected: -6.0010
Logits/chosen: -6.2132

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 8e-07
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 128
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

Transformers 4.44.2
Pytorch 2.7.0+cu128
Datasets 2.18.0
Tokenizers 0.19.1

Downloads last month: 5

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for jz666/simpo-train-large-wrong

Base model

google/gemma-2-9b

Finetuned

google/gemma-2-9b-it

Finetuned

(419)

this model

jz666
/

simpo-train-large-wrong

simpo-train-large-wrong

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for jz666/simpo-train-large-wrong

Dataset used to train jz666/simpo-train-large-wrong