Instructions to use LTC-AI-Labs/L2-7b-Hermes-Synthia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LTC-AI-Labs/L2-7b-Hermes-Synthia with Transformers:

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

pipe = pipeline("text-generation", model="LTC-AI-Labs/L2-7b-Hermes-Synthia")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LTC-AI-Labs/L2-7b-Hermes-Synthia")
model = AutoModelForCausalLM.from_pretrained("LTC-AI-Labs/L2-7b-Hermes-Synthia", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LTC-AI-Labs/L2-7b-Hermes-Synthia with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LTC-AI-Labs/L2-7b-Hermes-Synthia"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LTC-AI-Labs/L2-7b-Hermes-Synthia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LTC-AI-Labs/L2-7b-Hermes-Synthia

SGLang

How to use LTC-AI-Labs/L2-7b-Hermes-Synthia 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 "LTC-AI-Labs/L2-7b-Hermes-Synthia" \
    --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": "LTC-AI-Labs/L2-7b-Hermes-Synthia",
		"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 "LTC-AI-Labs/L2-7b-Hermes-Synthia" \
        --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": "LTC-AI-Labs/L2-7b-Hermes-Synthia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LTC-AI-Labs/L2-7b-Hermes-Synthia with Docker Model Runner:
```
docker model run hf.co/LTC-AI-Labs/L2-7b-Hermes-Synthia
```

Fine-tuned the synthia dataset on the hermes2 7b model

In my opinion it's probably the best model I fine-tuned in-terms of role-playing (tested on LavernAI)

Future plans:

I'll probably do more test in other areas
Will add other languages (Potentially japanese and chinese)
Finetune it on mistral models?

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.21
AI2 Reasoning Challenge (25-Shot)	51.02
HellaSwag (10-Shot)	79.12
MMLU (5-Shot)	47.88
TruthfulQA (0-shot)	46.77
Winogrande (5-shot)	74.51
GSM8k (5-shot)	13.95

Downloads last month: 82

Safetensors

Model size

7B params

Tensor type

F32

F16

Model tree for LTC-AI-Labs/L2-7b-Hermes-Synthia

Adapters

1 model

Datasets used to train LTC-AI-Labs/L2-7b-Hermes-Synthia

Evaluation results

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

51.020
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

79.120
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

47.880
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

46.770
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

74.510
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

13.950