Instructions to use SteelStorage/L3.3-MS-Evalebis-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SteelStorage/L3.3-MS-Evalebis-70b with Transformers:

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

pipe = pipeline("text-generation", model="SteelStorage/L3.3-MS-Evalebis-70b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SteelStorage/L3.3-MS-Evalebis-70b")
model = AutoModelForCausalLM.from_pretrained("SteelStorage/L3.3-MS-Evalebis-70b", 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 SteelStorage/L3.3-MS-Evalebis-70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SteelStorage/L3.3-MS-Evalebis-70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SteelStorage/L3.3-MS-Evalebis-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SteelStorage/L3.3-MS-Evalebis-70b

SGLang

How to use SteelStorage/L3.3-MS-Evalebis-70b 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 "SteelStorage/L3.3-MS-Evalebis-70b" \
    --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": "SteelStorage/L3.3-MS-Evalebis-70b",
		"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 "SteelStorage/L3.3-MS-Evalebis-70b" \
        --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": "SteelStorage/L3.3-MS-Evalebis-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SteelStorage/L3.3-MS-Evalebis-70b with Docker Model Runner:
```
docker model run hf.co/SteelStorage/L3.3-MS-Evalebis-70b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Creator: SteelSkull

About Evalebis-70b:

Name Legend:
L3.3 = Llama 3.3
MS = Model Stock
Evalebis = mix of EVA-LLAMA-0.1, EURYALE-v2.3 and Anubis-v1
70B = its 70B

This model was created as I liked the storytelling of EVA, the prose and details of scenes from EURYALE and Anubis, my goal is to merge the robust storytelling of all three models while attempting to maintain the positives of the models.

My recommended Templates / System prompts: (List of Prompt-Gremlins)

LLam@ception <<< Template / System prompt [Made by @.konnect]

DWK-SP0.02 <<< System prompt [Made by @daimonwk]

Quants: (List of badasses) [will add once created]

GGUF Quant:

- bartowski: Combined-GGUF

- mradermacher: GGUF // Imat-GGUF

Config:

MODEL_NAME = "L3.3-MS-Evayale-70B"
base_model: unsloth/Llama-3.3-70B-Instruct
merge_method: model_stock
dtype: bfloat16
models:
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
  - model: Sao10K/L3.3-70B-Euryale-v2.3
  - model: TheDrummer/Anubis-70B-v1

If you wish to support:

Downloads last month: 18

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for SteelStorage/L3.3-MS-Evalebis-70b

EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1

Sao10K/L3.3-70B-Euryale-v2.3

TheDrummer/Anubis-70B-v1

unsloth/Llama-3.3-70B-Instruct

Merge model

this model

Quantizations

3 models