Instructions to use LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2")
model = AutoModelForCausalLM.from_pretrained("LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2")
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 LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2

SGLang

How to use LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2 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 "LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2" \
    --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": "LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2",
		"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 "LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2" \
        --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": "LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2 with Docker Model Runner:
```
docker model run hf.co/LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2
```

NeuralHermes 2.5 - Mistral 7B

NeuralHermes is an teknium/OpenHermes-2.5-Mistral-7B model that has been further fine-tuned with Direct Preference Optimization (DPO) using the mlabonne/chatml_dpo_pairs dataset. It surpasses the original model on several benchmarks (see results).

It is directly inspired by the RLHF process described by Intel/neural-chat-7b-v3-1's authors to improve performance. I used the same dataset and reformatted it to apply the ChatML template.

The code to train this model is available on Google Colab and GitHub. It required an A100 GPU for about an hour.

Quantized models

Results

Teknium (author of OpenHermes-2.5-Mistral-7B) benchmarked the model (see his tweet).

Results are improved on every benchmark: AGIEval (from 43.07% to 43.62%), GPT4All (from 73.12% to 73.25%), and TruthfulQA.

AGIEval

GPT4All

TruthfulQA

You can check the Weights & Biases project here.

Usage

You can run this model using LM Studio or any other frontend.

You can also run this model using the following code:

import transformers
from transformers import AutoTokenizer

# Format prompt
message = [
    {"role": "system", "content": "You are a helpful assistant chatbot."},
    {"role": "user", "content": "What is a Large Language Model?"}
]
tokenizer = AutoTokenizer.from_pretrained(new_model)
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)

# Create pipeline
pipeline = transformers.pipeline(
    "text-generation",
    model=new_model,
    tokenizer=tokenizer
)

# Generate text
sequences = pipeline(
    prompt,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    num_return_sequences=1,
    max_length=200,
)
print(sequences[0]['generated_text'])

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:

per_device_train_batch_size=4
gradient_accumulation_steps=4
gradient_checkpointing=True
learning_rate=5e-5
lr_scheduler_type="cosine"
max_steps=200
optim="paged_adamw_32bit"
warmup_steps=100

DPOTrainer:

beta=0.1
max_prompt_length=1024
max_length=1536

Downloads last month: 3

Model tree for LoneStriker/NeuralHermes-2.5-Mistral-7B-8.0bpw-h8-exl2

Base model

mistralai/Mistral-7B-v0.1

Finetuned

teknium/OpenHermes-2.5-Mistral-7B