Instructions to use NickyNicky/OpenHermes_fourier_merge_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NickyNicky/OpenHermes_fourier_merge_v1 with Transformers:

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

pipe = pipeline("text-generation", model="NickyNicky/OpenHermes_fourier_merge_v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NickyNicky/OpenHermes_fourier_merge_v1")
model = AutoModelForCausalLM.from_pretrained("NickyNicky/OpenHermes_fourier_merge_v1", device_map="auto")
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 NickyNicky/OpenHermes_fourier_merge_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NickyNicky/OpenHermes_fourier_merge_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NickyNicky/OpenHermes_fourier_merge_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NickyNicky/OpenHermes_fourier_merge_v1

SGLang

How to use NickyNicky/OpenHermes_fourier_merge_v1 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 "NickyNicky/OpenHermes_fourier_merge_v1" \
    --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": "NickyNicky/OpenHermes_fourier_merge_v1",
		"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 "NickyNicky/OpenHermes_fourier_merge_v1" \
        --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": "NickyNicky/OpenHermes_fourier_merge_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NickyNicky/OpenHermes_fourier_merge_v1 with Docker Model Runner:
```
docker model run hf.co/NickyNicky/OpenHermes_fourier_merge_v1
```

Model Card for Model (OpenHermes_fourier_merge_v1)

models merge fourier :
    - model_1: "teknium/OpenHermes-2.5-Mistral-7B"
    - model_2: 'teknium/OpenHermes-2-Mistral-7B'


from transformers import AutoModelForCausalLM, AutoTokenizer,pipeline
import torch

model_id="NickyNicky/OpenHermes_fourier_merge_v1"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, 
                                             device_map="auto", 
                                             trust_remote_code=True,
                                            #  load_in_4bit=True,
                                             ).eval() #

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer

)

txt= "dame un ejemplo del lenguaje de programacion Python"

messages = [
    {"role": "user", "content":txt},
]
prompt = pipe.tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
res = pipe(
    prompt,
    max_new_tokens=2056,
    do_sample=True,
    temperature=0.31, # 0.31 # 0.41
)
print(res[0]["generated_text"])

Downloads last month: 9

Safetensors

Model size

7B params

Tensor type

F32