Instructions to use alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt with Transformers:

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

pipe = pipeline("text-generation", model="alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt")
model = AutoModelForMultimodalLM.from_pretrained("alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt")
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 alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt

SGLang

How to use alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt 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 "alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt" \
    --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": "alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt",
		"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 "alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt" \
        --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": "alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt with Docker Model Runner:
```
docker model run hf.co/alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt
```

mistral-orpo-mix-beta

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2152
Rewards/chosen: -0.1113
Rewards/rejected: -0.1461
Rewards/accuracies: 0.6562
Rewards/margins: 0.0348
Logps/rejected: -1.4607
Logps/chosen: -1.1130
Logits/rejected: -2.4201
Logits/chosen: -2.4178
Nll Loss: 1.1711
Log Odds Ratio: -0.6108
Log Odds Chosen: 0.5395

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: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: inverse_sqrt
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 100
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen	Nll Loss	Log Odds Ratio	Log Odds Chosen
0.9961	1.0	211	0.9199	-0.0831	-0.1055	0.6302	0.0224	-1.0547	-0.8311	-2.3542	-2.3590	0.8774	-0.6294	0.3896
0.4999	2.0	422	0.9813	-0.0894	-0.1184	0.6615	0.0290	-1.1836	-0.8937	-2.5184	-2.5177	0.9404	-0.6012	0.4994
0.1899	3.0	633	1.2152	-0.1113	-0.1461	0.6562	0.0348	-1.4607	-1.1130	-2.4201	-2.4178	1.1711	-0.6108	0.5395

Framework versions

Transformers 4.39.0
Pytorch 2.1.1+cu121
Datasets 2.16.1
Tokenizers 0.15.2

Downloads last month: 3

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(936)

this model

Space using alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt 1

Collection including alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt

About ORPO

Collection

Contains some information and experiments fine-tuning LLMs using 🤗 `trl.ORPOTrainer` • 7 items • Updated Mar 2 • 5