Instructions to use Steelskull/L3.3-Electra-R1-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Steelskull/L3.3-Electra-R1-70b with Transformers:

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

pipe = pipeline("text-generation", model="Steelskull/L3.3-Electra-R1-70b")
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("Steelskull/L3.3-Electra-R1-70b")
model = AutoModelForCausalLM.from_pretrained("Steelskull/L3.3-Electra-R1-70b", 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 Steelskull/L3.3-Electra-R1-70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Steelskull/L3.3-Electra-R1-70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Steelskull/L3.3-Electra-R1-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Steelskull/L3.3-Electra-R1-70b

SGLang

How to use Steelskull/L3.3-Electra-R1-70b 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 "Steelskull/L3.3-Electra-R1-70b" \
    --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": "Steelskull/L3.3-Electra-R1-70b",
		"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 "Steelskull/L3.3-Electra-R1-70b" \
        --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": "Steelskull/L3.3-Electra-R1-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Steelskull/L3.3-Electra-R1-70b with Docker Model Runner:
```
docker model run hf.co/Steelskull/L3.3-Electra-R1-70b
```

Steelskull commited on Mar 6, 2025

Commit

83e0fd6

verified ·

1 Parent(s): 2b3ab76

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -2205,7 +2205,7 @@ library_name: transformers
         <div class="template-card">
           <div class="template-item">
             <div class="template-content">
-              <a href="https://huggingface.co/Steelskull/L3.3-San-Mai-R1/resolve/main/Leception-XML-v1.json" target="_blank" class="template-link">
                 LeCeption v2
                 <span class="link-arrow">→</span>
               </a>
@@ -2221,13 +2221,18 @@ library_name: transformers
             <div class="settings-grid">
               <div class="settings-card">
                 <div class="settings-header">
-                  <h3>Start Reply With:</h3>
                 </div>
                 <div class="settings-content">
                   <div class="setting-item">
                     <p>'<span style="color: #00b2ff">&lt;think&gt;</span> OK, as an objective, detached narrative analyst, let's think this through carefully:'</p>
                   </div>
                 </div>
               </div>
               <div class="settings-card">
                 <div class="settings-header">

         <div class="template-card">
           <div class="template-item">
             <div class="template-content">
+              <a href="https://huggingface.co/TheSkullery/Unnamed-Exp-70b-v0.6.A/blob/main/LeCeption-XML-V2.json" target="_blank" class="template-link">
                 LeCeption v2
                 <span class="link-arrow">→</span>
               </a>
             <div class="settings-grid">
               <div class="settings-card">
                 <div class="settings-header">
+                  <h3>Start Reply With: (Either)</h3>
                 </div>
                 <div class="settings-content">
                   <div class="setting-item">
                     <p>'<span style="color: #00b2ff">&lt;think&gt;</span> OK, as an objective, detached narrative analyst, let's think this through carefully:'</p>
                   </div>
                 </div>
+                <div class="settings-content">
+                  <div class="setting-item">
+                    <p>'<span style="color: #00b2ff">&lt;think&gt;</span> OK, the user is asking'</p>
+                  </div>
+                </div>
               </div>
               <div class="settings-card">
                 <div class="settings-header">