Instructions to use leafspark/WizardHermes-2-Pro-Llama-3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with Transformers:

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

pipe = pipeline("text-generation", model="leafspark/WizardHermes-2-Pro-Llama-3-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("leafspark/WizardHermes-2-Pro-Llama-3-8b", dtype="auto")

llama-cpp-python

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="leafspark/WizardHermes-2-Pro-Llama-3-8b",
	filename="WizardHermes-2-Pro-Llama-3-8b.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

Use Docker

docker model run hf.co/leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

LM Studio
Jan

vLLM

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leafspark/WizardHermes-2-Pro-Llama-3-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/WizardHermes-2-Pro-Llama-3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

SGLang

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b 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 "leafspark/WizardHermes-2-Pro-Llama-3-8b" \
    --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": "leafspark/WizardHermes-2-Pro-Llama-3-8b",
		"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 "leafspark/WizardHermes-2-Pro-Llama-3-8b" \
        --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": "leafspark/WizardHermes-2-Pro-Llama-3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with Ollama:
```
ollama run hf.co/leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M
```

Unsloth Studio

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for leafspark/WizardHermes-2-Pro-Llama-3-8b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for leafspark/WizardHermes-2-Pro-Llama-3-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for leafspark/WizardHermes-2-Pro-Llama-3-8b to start chatting

Atomic Chat new
Docker Model Runner
How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with Docker Model Runner:
```
docker model run hf.co/leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M
```

Lemonade

How to use leafspark/WizardHermes-2-Pro-Llama-3-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull leafspark/WizardHermes-2-Pro-Llama-3-8b:Q4_K_M

Run and chat with the model

lemonade run user.WizardHermes-2-Pro-Llama-3-8b-Q4_K_M

List all available models

lemonade list

WizardHermes-2-Pro-Llama-3-8b

Finetuned from Meta-Llama-3-8b, 0.55 epoches

Merged with Hermes-2-Pro-Llama-3-8b

Eval (0.0 temp) (https://inflection.ai/assets/MMLU-Examples.pdf, 0-shot):

Hermes 2 Pro LoRA (merged) (checkpoint 1): 7/12
Hermes 2 Pro LoRA (merged) (checkpoint 2): 9/12
Hermes 2 Pro Llama 3 8b: 8/12

TruthfulQA (0-shot):

Hermes 2 Pro LoRA (merged) (checkpoint 2): 9/15
Hermes 2 Pro Llama 3 8b: 7/15

Trained using MonsterAPI

LoRA training parameters:

{
    "deployment_name": "wizardlm-llama-3-8b",
    "pretrainedmodel_config": {
        "model_path": "meta-llama/Meta-Llama-3-8B",
        "other_model_info": null,
        "resume_checkpoint_path": "",
        "use_lora": true,
        "lora_r": 8,
        "lora_alpha": 16,
        "lora_dropout": 0,
        "lora_bias": "none",
        "use_quantization": false,
        "use_gradient_checkpointing": false,
        "parallelization": "nmp"
    },
    "data_config": {
        "data_path": "cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered",
        "data_subset": "default",
        "data_source_type": "hub_link",
        "cutoff_len": 4096,
        "data_split_config": {
            "train": 0.9,
            "validation": 0.1
        },
        "prevalidated": true,
        "concat_config": {
            "0": {
                "text": "Below is an instruction that describes a task. Write a response that appropriately completes the request. \n\n\n###Instruction:",
                "column": false
            },
            "1": {
                "text": "instruction",
                "column": true
            },
            "2": {
                "text": "\n\n\n###Response:",
                "column": false
            },
            "3": {
                "text": "output",
                "column": true
            }
        }
    },
    "training_config": {
        "early_stopping_patience": 5,
        "num_train_epochs": 5,
        "gradient_accumulation_steps": 1,
        "warmup_steps": 300,
        "learning_rate": 0.0005,
        "lr_scheduler_type": "reduce_lr_on_plateau",
        "group_by_length": false,
        "use_hugging_face": false
    },
    "logging_config": {
        "use_wandb": false,
        "wandb_username": "",
        "wandb_login_key": "",
        "wandb_project": "",
        "wandb_run_name": ""
    },
    "accessorytasks_config": {
        "run_eval_report": false,
        "run_quantize_merge": false
    }
}

Downloads last month: 12

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

6-bit

8-bit

16-bit

Dataset used to train leafspark/WizardHermes-2-Pro-Llama-3-8b

Collection including leafspark/WizardHermes-2-Pro-Llama-3-8b

Llama 3 Experiments

Collection

3 items • Updated May 20, 2024