Instructions to use udgamlabs/Laghu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use udgamlabs/Laghu with Transformers:

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

pipe = pipeline("text-generation", model="udgamlabs/Laghu")
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("udgamlabs/Laghu")
model = AutoModelForCausalLM.from_pretrained("udgamlabs/Laghu", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use udgamlabs/Laghu with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/udgamlabs/Laghu

SGLang

How to use udgamlabs/Laghu 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 "udgamlabs/Laghu" \
    --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": "udgamlabs/Laghu",
		"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 "udgamlabs/Laghu" \
        --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": "udgamlabs/Laghu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use udgamlabs/Laghu with Docker Model Runner:
```
docker model run hf.co/udgamlabs/Laghu
```

Laghu / config.json

jiteshkprasad

Stage Laghu release files (private)

2da732c verified 2 days ago

Raw History Blame Contribute Delete

2.1 kB

{
  "architectures": [
    "Gemma4ForCausalLM"
  ],
  "model_type": "gemma4_text",
  "vocab_size": 32768,
  "hidden_size": 640,
  "intermediate_size": 1792,
  "num_hidden_layers": 28,
  "num_attention_heads": 10,
  "num_key_value_heads": 2,
  "head_dim": 64,
  "global_head_dim": 128,
  "per_layer_config": {
    "3": {
      "head_dim": 128
    },
    "7": {
      "head_dim": 128
    },
    "11": {
      "head_dim": 128
    },
    "15": {
      "head_dim": 128
    },
    "19": {
      "head_dim": 128
    },
    "23": {
      "head_dim": 128
    },
    "27": {
      "head_dim": 128
    }
  },
  "hidden_activation": "gelu_pytorch_tanh",
  "max_position_embeddings": 16384,
  "rms_norm_eps": 1e-06,
  "sliding_window": 512,
  "layer_types": [
    "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"
  ],
  "final_logit_softcapping": 15.0,
  "tie_word_embeddings": true,
  "hidden_size_per_layer_input": 0,
  "vocab_size_per_layer_input": 32768,
  "num_kv_shared_layers": 0,
  "use_double_wide_mlp": false,
  "attention_k_eq_v": false,
  "enable_moe_block": false,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "use_cache": true,
  "rope_parameters": {
    "sliding_attention": {
      "rope_type": "default",
      "rope_theta": 10000.0
    },
    "full_attention": {
      "rope_type": "proportional",
      "partial_rotary_factor": 1.0,
      "rope_theta": 1000000.0
    }
  },
  "pad_token_id": 0,
  "eos_token_id": 1,
  "bos_token_id": 2,
  "dtype": "bfloat16"
}

	{
	"architectures": [
	"Gemma4ForCausalLM"
	],
	"model_type": "gemma4_text",
	"vocab_size": 32768,
	"hidden_size": 640,
	"intermediate_size": 1792,
	"num_hidden_layers": 28,
	"num_attention_heads": 10,
	"num_key_value_heads": 2,
	"head_dim": 64,
	"global_head_dim": 128,
	"per_layer_config": {
	"3": {
	"head_dim": 128
	},
	"7": {
	"head_dim": 128
	},
	"11": {
	"head_dim": 128
	},
	"15": {
	"head_dim": 128
	},
	"19": {
	"head_dim": 128
	},
	"23": {
	"head_dim": 128
	},
	"27": {
	"head_dim": 128
	}
	},
	"hidden_activation": "gelu_pytorch_tanh",
	"max_position_embeddings": 16384,
	"rms_norm_eps": 1e-06,
	"sliding_window": 512,
	"layer_types": [
	"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"
	],
	"final_logit_softcapping": 15.0,
	"tie_word_embeddings": true,
	"hidden_size_per_layer_input": 0,
	"vocab_size_per_layer_input": 32768,
	"num_kv_shared_layers": 0,
	"use_double_wide_mlp": false,
	"attention_k_eq_v": false,
	"enable_moe_block": false,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"use_cache": true,
	"rope_parameters": {
	"sliding_attention": {
	"rope_type": "default",
	"rope_theta": 10000.0
	},
	"full_attention": {
	"rope_type": "proportional",
	"partial_rotary_factor": 1.0,
	"rope_theta": 1000000.0
	}
	},
	"pad_token_id": 0,
	"eos_token_id": 1,
	"bos_token_id": 2,
	"dtype": "bfloat16"
	}