Instructions to use hedronstone/OpenHermes-7B-Symbolic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hedronstone/OpenHermes-7B-Symbolic with Transformers:

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

pipe = pipeline("text-generation", model="hedronstone/OpenHermes-7B-Symbolic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hedronstone/OpenHermes-7B-Symbolic")
model = AutoModelForCausalLM.from_pretrained("hedronstone/OpenHermes-7B-Symbolic", 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 hedronstone/OpenHermes-7B-Symbolic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hedronstone/OpenHermes-7B-Symbolic

SGLang

How to use hedronstone/OpenHermes-7B-Symbolic 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 "hedronstone/OpenHermes-7B-Symbolic" \
    --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": "hedronstone/OpenHermes-7B-Symbolic",
		"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 "hedronstone/OpenHermes-7B-Symbolic" \
        --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": "hedronstone/OpenHermes-7B-Symbolic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hedronstone/OpenHermes-7B-Symbolic with Docker Model Runner:
```
docker model run hf.co/hedronstone/OpenHermes-7B-Symbolic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenHermes-7B-Symbolic

Model description

OpenHermes-7B-Symbolic is a OpenHermes-2.5-Mistral-7B fine-tuned on 93K comprehensive and meticulously curated samples. Each sample was structured to facilitate the model's understanding and generation of complex, hierarchical ICD medical coding system.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	64.44
AI2 Reasoning Challenge (25-Shot)	63.14
HellaSwag (10-Shot)	82.73
MMLU (5-Shot)	62.62
TruthfulQA (0-shot)	48.82
Winogrande (5-shot)	75.85
GSM8k (5-shot)	53.45

Downloads last month: 53

Safetensors

Model size

7B params

Tensor type

F16

Model tree for hedronstone/OpenHermes-7B-Symbolic

Quantizations

3 models

Space using hedronstone/OpenHermes-7B-Symbolic 1

Evaluation results

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

63.140
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

82.730
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

62.620
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

48.820
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

75.850
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

53.450