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)

# pip install -U transformers accelerate
# 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=256)
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
```

Steelskull commited on Dec 30, 2024

Commit

78e9f67

verified ·

1 Parent(s): 3cb35c6

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -127,7 +127,7 @@ Evalebis = mix of EVA-LLAMA-0.1, EURYALE-v2.3 and Anubis-v1
        <h2>Quants: (List of badasses) [will add once created]</h2>
       <p>GGUF Quant: </p>
        <p>    - bartowski: <a href="https://huggingface.co/bartowski/L3.3-MS-Evalebis-70b-GGUF" target="_blank"> Combined-GGUF </a></p>
-       <<p>    - mradermacher: <a href="https://huggingface.co/mradermacher/L3.3-MS-Evalebis-70b-GGUF" target="_blank"> GGUF </a>// <a href="https://huggingface.co/mradermacher/L3.3-MS-Evalebis-70b-i1-GGUF" target="_blank"> Imat-GGUF </a></p>
       <h3>Config:</h3>
       <pre><code>MODEL_NAME = "L3.3-MS-Evayale-70B"
 base_model: unsloth/Llama-3.3-70B-Instruct

        <h2>Quants: (List of badasses) [will add once created]</h2>
       <p>GGUF Quant: </p>
        <p>    - bartowski: <a href="https://huggingface.co/bartowski/L3.3-MS-Evalebis-70b-GGUF" target="_blank"> Combined-GGUF </a></p>
+       <p>    - mradermacher: <a href="https://huggingface.co/mradermacher/L3.3-MS-Evalebis-70b-GGUF" target="_blank"> GGUF </a>// <a href="https://huggingface.co/mradermacher/L3.3-MS-Evalebis-70b-i1-GGUF" target="_blank"> Imat-GGUF </a></p>
       <h3>Config:</h3>
       <pre><code>MODEL_NAME = "L3.3-MS-Evayale-70B"
 base_model: unsloth/Llama-3.3-70B-Instruct