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 / config.json

tcclaviger

Update config.json

f73cde0 verified 4 days ago

Raw

History Blame Contribute Delete

5.85 kB

	{
	"architectures": [
	"LagunaForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_laguna.LagunaConfig",
	"AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
	},
	"model_type": "laguna",
	"vocab_size": 100352,
	"hidden_size": 3072,
	"intermediate_size": 12288,
	"num_hidden_layers": 48,
	"num_attention_heads": 48,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"max_position_embeddings": 1048576,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"rms_norm_eps": 1e-06,
	"num_experts": 256,
	"num_experts_per_tok": 10,
	"moe_intermediate_size": 1024,
	"shared_expert_intermediate_size": 1024,
	"norm_topk_prob": true,
	"router_aux_loss_coef": 0.0,
	"decoder_sparse_step": 1,
	"mlp_only_layers": [
	0
	],
	"bos_token_id": 2,
	"eos_token_id": [
	2,
	24
	],
	"pad_token_id": 9,
	"tie_word_embeddings": false,
	"use_cache": true,
	"torch_dtype": "bfloat16",
	"gating": "per-head",
	"sliding_window": 512,
	"rope_parameters": {
	"full_attention": {
	"rope_theta": 500000.0,
	"rope_type": "yarn",
	"factor": 128.0,
	"original_max_position_embeddings": 8192,
	"beta_slow": 1.0,
	"beta_fast": 32.0,
	"attention_factor": 1.4852030263919618,
	"partial_rotary_factor": 0.5
	},
	"sliding_attention": {
	"rope_type": "default",
	"rope_theta": 10000.0,
	"partial_rotary_factor": 1.0
	}
	},
	"layer_types": [
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"moe_apply_router_weight_on_input": false,
	"mlp_layer_types": [
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"gating_types": [
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head",
	"per_head"
	],
	"moe_routed_scaling_factor": 2.5,
	"num_attention_heads_per_layer": [
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72,
	48,
	72,
	72,
	72
	],
	"moe_router_logit_softcapping": 0.0,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "rfa-pack-quantized",
	"input_activations": null,
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"num_bits": 4,
	"type": "float",
	"group_size": 16,
	"grid": "iq4_nl",
	"codebook": [
	-127,
	-104,
	-83,
	-65,
	-49,
	-35,
	-22,
	-10,
	1,
	13,
	25,
	38,
	53,
	69,
	89,
	113
	],
	"scale_dtype": "torch.int8",
	"scale_exp_dtype": "torch.int8",
	"scale_encoding": "block_float_i8m_i8e",
	"symmetric": false,
	"rotation": "hadamard16"
	}
	}
	},
	"format": "rfa-pack-quantized",
	"quant_method": "rfa",
	"quantization_status": "compressed",
	"version": "rfa-1.0",
	"ignore": [
	"re:.\\.self_attn\\..",
	"re:.*\\.mlp\\.gate\\.weight$",
	"re:^lm_head",
	"re:.\\.mlp\\.shared_expert\\..",
	"re:.\\.layers\\.0\\.mlp\\.."
	]
	}
	}