Instructions to use PointGuardAI/LFM2.5-1.2B-Instruct-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PointGuardAI/LFM2.5-1.2B-Instruct-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="PointGuardAI/LFM2.5-1.2B-Instruct-INT8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PointGuardAI/LFM2.5-1.2B-Instruct-INT8")
model = AutoModelForCausalLM.from_pretrained("PointGuardAI/LFM2.5-1.2B-Instruct-INT8", 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 PointGuardAI/LFM2.5-1.2B-Instruct-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PointGuardAI/LFM2.5-1.2B-Instruct-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PointGuardAI/LFM2.5-1.2B-Instruct-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PointGuardAI/LFM2.5-1.2B-Instruct-INT8

SGLang

How to use PointGuardAI/LFM2.5-1.2B-Instruct-INT8 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 "PointGuardAI/LFM2.5-1.2B-Instruct-INT8" \
    --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": "PointGuardAI/LFM2.5-1.2B-Instruct-INT8",
		"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 "PointGuardAI/LFM2.5-1.2B-Instruct-INT8" \
        --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": "PointGuardAI/LFM2.5-1.2B-Instruct-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PointGuardAI/LFM2.5-1.2B-Instruct-INT8 with Docker Model Runner:
```
docker model run hf.co/PointGuardAI/LFM2.5-1.2B-Instruct-INT8
```

LFM2.5-1.2B-Instruct-INT8 / config.json

shubham-kothari

Publish LFM2.5-1.2B-Instruct W8A8 INT8 checkpoint

f1eb922 verified 7 days ago

Raw

History Blame Contribute Delete

6.56 kB

	{
	"architectures": [
	"Lfm2ForCausalLM"
	],
	"block_auto_adjust_ff_dim": true,
	"block_dim": 2048,
	"block_ffn_dim_multiplier": 1.0,
	"block_mlp_init_scale": 1.0,
	"block_multiple_of": 256,
	"block_norm_eps": 1e-05,
	"block_out_init_scale": 1.0,
	"block_use_swiglu": true,
	"block_use_xavier_init": true,
	"bos_token_id": 1,
	"conv_L_cache": 3,
	"conv_bias": false,
	"conv_dim": 2048,
	"conv_use_xavier_init": true,
	"dtype": "bfloat16",
	"eos_token_id": 7,
	"full_attn_idxs": null,
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv",
	"full_attention",
	"conv"
	],
	"max_position_embeddings": 128000,
	"model_type": "lfm2",
	"norm_eps": 1e-05,
	"num_attention_heads": 32,
	"num_heads": 32,
	"num_hidden_layers": 16,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "int-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": null,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "token",
	"symmetric": true,
	"type": "int",
	"zp_dtype": null
	},
	"output_activations": null,
	"targets": [
	"model.layers.0.feed_forward.w1",
	"model.layers.0.feed_forward.w2",
	"model.layers.0.feed_forward.w3",
	"model.layers.1.feed_forward.w1",
	"model.layers.1.feed_forward.w2",
	"model.layers.1.feed_forward.w3",
	"model.layers.10.feed_forward.w1",
	"model.layers.10.feed_forward.w2",
	"model.layers.10.feed_forward.w3",
	"model.layers.10.self_attn.k_proj",
	"model.layers.10.self_attn.out_proj",
	"model.layers.10.self_attn.q_proj",
	"model.layers.10.self_attn.v_proj",
	"model.layers.11.feed_forward.w1",
	"model.layers.11.feed_forward.w2",
	"model.layers.11.feed_forward.w3",
	"model.layers.12.feed_forward.w1",
	"model.layers.12.feed_forward.w2",
	"model.layers.12.feed_forward.w3",
	"model.layers.12.self_attn.k_proj",
	"model.layers.12.self_attn.out_proj",
	"model.layers.12.self_attn.q_proj",
	"model.layers.12.self_attn.v_proj",
	"model.layers.13.feed_forward.w1",
	"model.layers.13.feed_forward.w2",
	"model.layers.13.feed_forward.w3",
	"model.layers.14.feed_forward.w1",
	"model.layers.14.feed_forward.w2",
	"model.layers.14.feed_forward.w3",
	"model.layers.14.self_attn.k_proj",
	"model.layers.14.self_attn.out_proj",
	"model.layers.14.self_attn.q_proj",
	"model.layers.14.self_attn.v_proj",
	"model.layers.15.feed_forward.w1",
	"model.layers.15.feed_forward.w2",
	"model.layers.15.feed_forward.w3",
	"model.layers.2.feed_forward.w1",
	"model.layers.2.feed_forward.w2",
	"model.layers.2.feed_forward.w3",
	"model.layers.2.self_attn.k_proj",
	"model.layers.2.self_attn.out_proj",
	"model.layers.2.self_attn.q_proj",
	"model.layers.2.self_attn.v_proj",
	"model.layers.3.feed_forward.w1",
	"model.layers.3.feed_forward.w2",
	"model.layers.3.feed_forward.w3",
	"model.layers.4.feed_forward.w1",
	"model.layers.4.feed_forward.w2",
	"model.layers.4.feed_forward.w3",
	"model.layers.5.feed_forward.w1",
	"model.layers.5.feed_forward.w2",
	"model.layers.5.feed_forward.w3",
	"model.layers.5.self_attn.k_proj",
	"model.layers.5.self_attn.out_proj",
	"model.layers.5.self_attn.q_proj",
	"model.layers.5.self_attn.v_proj",
	"model.layers.6.feed_forward.w1",
	"model.layers.6.feed_forward.w2",
	"model.layers.6.feed_forward.w3",
	"model.layers.7.feed_forward.w1",
	"model.layers.7.feed_forward.w2",
	"model.layers.7.feed_forward.w3",
	"model.layers.8.feed_forward.w1",
	"model.layers.8.feed_forward.w2",
	"model.layers.8.feed_forward.w3",
	"model.layers.8.self_attn.k_proj",
	"model.layers.8.self_attn.out_proj",
	"model.layers.8.self_attn.q_proj",
	"model.layers.8.self_attn.v_proj",
	"model.layers.9.feed_forward.w1",
	"model.layers.9.feed_forward.w2",
	"model.layers.9.feed_forward.w3"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "channel",
	"symmetric": true,
	"type": "int",
	"zp_dtype": null
	}
	}
	},
	"format": "int-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"model.layers.0.conv.in_proj",
	"model.layers.0.conv.out_proj",
	"model.layers.1.conv.in_proj",
	"model.layers.1.conv.out_proj",
	"model.layers.3.conv.in_proj",
	"model.layers.3.conv.out_proj",
	"model.layers.4.conv.in_proj",
	"model.layers.4.conv.out_proj",
	"model.layers.6.conv.in_proj",
	"model.layers.6.conv.out_proj",
	"model.layers.7.conv.in_proj",
	"model.layers.7.conv.out_proj",
	"model.layers.9.conv.in_proj",
	"model.layers.9.conv.out_proj",
	"model.layers.11.conv.in_proj",
	"model.layers.11.conv.out_proj",
	"model.layers.13.conv.in_proj",
	"model.layers.13.conv.out_proj",
	"model.layers.15.conv.in_proj",
	"model.layers.15.conv.out_proj",
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.17.1"
	},
	"rope_parameters": {
	"rope_theta": 1000000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.10.1",
	"use_cache": true,
	"use_pos_enc": true,
	"vocab_size": 65536
	}