Instructions to use tcclaviger/Laguna-S-2.1-RFA_L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tcclaviger/Laguna-S-2.1-RFA_L with Transformers:

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

pipe = pipeline("text-generation", model="tcclaviger/Laguna-S-2.1-RFA_L", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tcclaviger/Laguna-S-2.1-RFA_L", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tcclaviger/Laguna-S-2.1-RFA_L", trust_remote_code=True, 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 tcclaviger/Laguna-S-2.1-RFA_L with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tcclaviger/Laguna-S-2.1-RFA_L"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tcclaviger/Laguna-S-2.1-RFA_L",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tcclaviger/Laguna-S-2.1-RFA_L

SGLang

How to use tcclaviger/Laguna-S-2.1-RFA_L 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 "tcclaviger/Laguna-S-2.1-RFA_L" \
    --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": "tcclaviger/Laguna-S-2.1-RFA_L",
		"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 "tcclaviger/Laguna-S-2.1-RFA_L" \
        --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": "tcclaviger/Laguna-S-2.1-RFA_L",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tcclaviger/Laguna-S-2.1-RFA_L with Docker Model Runner:
```
docker model run hf.co/tcclaviger/Laguna-S-2.1-RFA_L
```

Laguna-S-2.1-RFA_L

File size: 1,211 Bytes

d891c8d

=== Laguna-S-2.1-RFA ===
arch: laguna
codebook: [-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113]
rotation: hadamard16

[integrity] shards=13 missing=none
[integrity] index total_size=71.16GB  on-disk safetensors sum=71.17GB
[integrity] tensors: index=109249 headers=109249 OK

[coverage] quantized expert-mods=0 linear-mods=36240 fp16-protected=0 copied=529
[coverage] missing/bad: 0

[bpw] quant-target params=114.10B  rfa bytes=64.25GB  -> 4.504 bits/weight
[size] total=71.16GB = rfa 64.25GB + copied(bf16/other) 6.91GB

[fidelity] dequant vs source (relFro / SQNR):
   model.layers.0.mlp.down_proj  relFro=6.150%  SQNR=24.2 dB
   model.layers.0.mlp.gate_proj  relFro=6.311%  SQNR=24.0 dB
   model.layers.0.mlp.up_proj  relFro=6.304%  SQNR=24.0 dB
   model.layers.24.mlp.experts.0.down_proj  relFro=6.328%  SQNR=24.0 dB
   model.layers.24.mlp.experts.0.gate_proj  relFro=6.334%  SQNR=24.0 dB
   model.layers.24.mlp.experts.0.up_proj  relFro=6.335%  SQNR=24.0 dB
   model.layers.47.mlp.experts.0.down_proj  relFro=6.338%  SQNR=24.0 dB
   model.layers.47.mlp.experts.0.gate_proj  relFro=6.340%  SQNR=24.0 dB
   model.layers.47.mlp.experts.0.up_proj  relFro=6.336%  SQNR=24.0 dB

DONE