Instructions to use steinzer-narayan/fimbulhermes-15B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use steinzer-narayan/fimbulhermes-15B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="steinzer-narayan/fimbulhermes-15B-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("steinzer-narayan/fimbulhermes-15B-v0.1")
model = AutoModelForCausalLM.from_pretrained("steinzer-narayan/fimbulhermes-15B-v0.1", 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 steinzer-narayan/fimbulhermes-15B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "steinzer-narayan/fimbulhermes-15B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "steinzer-narayan/fimbulhermes-15B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/steinzer-narayan/fimbulhermes-15B-v0.1

SGLang

How to use steinzer-narayan/fimbulhermes-15B-v0.1 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 "steinzer-narayan/fimbulhermes-15B-v0.1" \
    --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": "steinzer-narayan/fimbulhermes-15B-v0.1",
		"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 "steinzer-narayan/fimbulhermes-15B-v0.1" \
        --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": "steinzer-narayan/fimbulhermes-15B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use steinzer-narayan/fimbulhermes-15B-v0.1 with Docker Model Runner:
```
docker model run hf.co/steinzer-narayan/fimbulhermes-15B-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

FimbulHermes-15B-v0.1

This is a merge of two of the best SOLAR derivatives, created using mergekit.

The model is stable and expressive, but has not been thoroughly evaluated.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
    - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
      layer_range: [0, 16]
  - sources:
    - model: "Sao10K/Fimbulvetr-11B-v2"
      layer_range: [8, 24]
  - sources:
    - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
      layer_range: [17, 32]
  - sources:
    - model: "Sao10K/Fimbulvetr-11B-v2"
      layer_range: [25, 40]
  - sources:
    - model: "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
      layer_range: [41, 48]
merge_method: passthrough
dtype: float16

Downloads last month: 12

Safetensors

Model size

15B params

Tensor type

F16

Model tree for steinzer-narayan/fimbulhermes-15B-v0.1

NousResearch/Nous-Hermes-2-SOLAR-10.7B

Sao10K/Fimbulvetr-11B-v2

Merge model

this model

Quantizations

1 model