Instructions to use vicgalle/OpenHermes-Qwen1.5-1.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicgalle/OpenHermes-Qwen1.5-1.8B with Transformers:

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

pipe = pipeline("text-generation", model="vicgalle/OpenHermes-Qwen1.5-1.8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("vicgalle/OpenHermes-Qwen1.5-1.8B")
model = AutoModelForMultimodalLM.from_pretrained("vicgalle/OpenHermes-Qwen1.5-1.8B")
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 vicgalle/OpenHermes-Qwen1.5-1.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicgalle/OpenHermes-Qwen1.5-1.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vicgalle/OpenHermes-Qwen1.5-1.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicgalle/OpenHermes-Qwen1.5-1.8B

SGLang

How to use vicgalle/OpenHermes-Qwen1.5-1.8B 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 "vicgalle/OpenHermes-Qwen1.5-1.8B" \
    --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": "vicgalle/OpenHermes-Qwen1.5-1.8B",
		"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 "vicgalle/OpenHermes-Qwen1.5-1.8B" \
        --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": "vicgalle/OpenHermes-Qwen1.5-1.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vicgalle/OpenHermes-Qwen1.5-1.8B with Docker Model Runner:
```
docker model run hf.co/vicgalle/OpenHermes-Qwen1.5-1.8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	44.95
AI2 Reasoning Challenge (25-Shot)	37.80
HellaSwag (10-Shot)	59.73
MMLU (5-Shot)	45.80
TruthfulQA (0-shot)	42.28
Winogrande (5-shot)	60.22
GSM8k (5-shot)	23.88

Downloads last month: 104

Safetensors

Model size

2B params

Tensor type

F16

Model tree for vicgalle/OpenHermes-Qwen1.5-1.8B

Quantizations

2 models

Dataset used to train vicgalle/OpenHermes-Qwen1.5-1.8B

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

37.800
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

59.730
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

45.800
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

42.280
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

60.220
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

23.880