Instructions to use sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered with Transformers:

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

pipe = pipeline("text-generation", model="sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered")
model = AutoModelForCausalLM.from_pretrained("sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered

SGLang

How to use sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered 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 "sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered" \
    --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": "sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered",
		"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 "sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered" \
        --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": "sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered with Docker Model Runner:
```
docker model run hf.co/sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Training hyperparameters LoRA: r=16 lora_alpha=16 lora_dropout=0.05 bias="none" task_type="CAUSAL_LM" target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']

Training arguments: auto_find_batch_size=True gradient_checkpointing=True learning_rate=5e-7 lr_scheduler_type="cosine" max_steps=3922 optim="paged_adamw_32bit" warmup_steps=100

DPOTrainer: beta=0.1 max_prompt_length=1024 max_length=1536

Arxiv link: https://arxiv.org/abs/2403.02745

Downloads last month: 64

Safetensors

Model size

7B params

Tensor type

F16

Model tree for sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered

Quantizations

2 models

Paper for sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered

CURATRON: Complete Robust Preference Data for Robust Alignment of Large Language Models

Paper • 2403.02745 • Published Mar 5, 2024 • 1