NousHermes_4.3_36B_Lab

Instructions to use Babsie/NousHermes_4.3_36B_Lab with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Babsie/NousHermes_4.3_36B_Lab with Transformers:

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

pipe = pipeline("text-generation", model="Babsie/NousHermes_4.3_36B_Lab")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Babsie/NousHermes_4.3_36B_Lab")
model = AutoModelForCausalLM.from_pretrained("Babsie/NousHermes_4.3_36B_Lab", 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 Babsie/NousHermes_4.3_36B_Lab with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Babsie/NousHermes_4.3_36B_Lab"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Babsie/NousHermes_4.3_36B_Lab",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Babsie/NousHermes_4.3_36B_Lab

SGLang

How to use Babsie/NousHermes_4.3_36B_Lab 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 "Babsie/NousHermes_4.3_36B_Lab" \
    --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": "Babsie/NousHermes_4.3_36B_Lab",
		"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 "Babsie/NousHermes_4.3_36B_Lab" \
        --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": "Babsie/NousHermes_4.3_36B_Lab",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Babsie/NousHermes_4.3_36B_Lab with Docker Model Runner:
```
docker model run hf.co/Babsie/NousHermes_4.3_36B_Lab
```

Babsie commited on Mar 5

Commit

968537e

verified ·

1 Parent(s): f648c0e

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -0

README.md CHANGED Viewed

@@ -33,6 +33,14 @@ model-index:
 - name: Hermes-4.3-ByteDance-Seed-36B
   results: []
 ---
 # Hermes 4.3 - Seed 36B

 - name: Hermes-4.3-ByteDance-Seed-36B
   results: []
 ---
+# This Model is a Lab Model for my weird arse development project
+If you want Hermes 4.3 36B please go to [NousResearch/Hermes-4.3-36B](https://huggingface.co/NousResearch/Hermes-4.3-36B)
+- It's going to be a long while before it's ready, and I don't even know if it will be publicly applicable as it's aimed for those with neuroatypical accessibily issues like myself.
+- There are three others I am working on.
+- Getting my drive wiped back in Dec really hurt my Lab and it's been a long rebuild. Been a steep learning curve with the new research papers as well.
+Hope to be able to share perhaps the 14B at the very least.
+- Babs.
 # Hermes 4.3 - Seed 36B