Instructions to use sandmanbuzz/lesser-hermes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandmanbuzz/lesser-hermes with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sandmanbuzz/lesser-hermes")
model = AutoModelForCausalLM.from_pretrained("sandmanbuzz/lesser-hermes")
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

vLLM

How to use sandmanbuzz/lesser-hermes with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sandmanbuzz/lesser-hermes

SGLang

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

Docker Model Runner
How to use sandmanbuzz/lesser-hermes with Docker Model Runner:
```
docker model run hf.co/sandmanbuzz/lesser-hermes
```

lesser-hermes

Why?

Hermes is very, um, Hermes-y. I wanted to dilute it so I could use it as an ingredient for other things. Sampling Hermes is a pain in the ass, it either sounds super model-esque or it loses all instructability. Hence, dilution back to the root.

This is a merge of pre-trained language models created using mergekit. We've been using this as one of the experimental ingredients to help stabilize the monkey-typewriter merges, and it's kinda okay at that.

Note that modern mergekit handles MoE just fine, now. But back in the day it did a horrible job and only the fork worked properly.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mistralai/Mixtral-8x7B-Instruct-v0.1 as a base.

Models Merged

The following models were included in the merge:

NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO

Configuration

The following YAML configuration was used to produce this model:

models:
  # dont bagel me bro
  - model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
    parameters:
      density: 0.25
      weight: 0.3
  - model: mistralai/Mixtral-8x7B-Instruct-v0.1
    parameters:
      density: 0.5
      weight: 1
merge_method: dare_ties
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
parameters:
  #normalize: false
  #int8_mask: true
dtype: bfloat16

Downloads last month: 6

Safetensors

Model size

47B params

Tensor type

BF16

Model tree for sandmanbuzz/lesser-hermes

NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO

mistralai/Mixtral-8x7B-Instruct-v0.1

Merge model

this model

Papers for sandmanbuzz/lesser-hermes

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 33

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19