Instructions to use Nichonauta/LFM2.5-230M-ToMoE-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nichonauta/LFM2.5-230M-ToMoE-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="Nichonauta/LFM2.5-230M-ToMoE-INT4", 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("Nichonauta/LFM2.5-230M-ToMoE-INT4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Nichonauta/LFM2.5-230M-ToMoE-INT4", 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 Nichonauta/LFM2.5-230M-ToMoE-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nichonauta/LFM2.5-230M-ToMoE-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nichonauta/LFM2.5-230M-ToMoE-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nichonauta/LFM2.5-230M-ToMoE-INT4

SGLang

How to use Nichonauta/LFM2.5-230M-ToMoE-INT4 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 "Nichonauta/LFM2.5-230M-ToMoE-INT4" \
    --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": "Nichonauta/LFM2.5-230M-ToMoE-INT4",
		"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 "Nichonauta/LFM2.5-230M-ToMoE-INT4" \
        --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": "Nichonauta/LFM2.5-230M-ToMoE-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nichonauta/LFM2.5-230M-ToMoE-INT4 with Docker Model Runner:
```
docker model run hf.co/Nichonauta/LFM2.5-230M-ToMoE-INT4
```

Nichonauta commited on 2 days ago

Commit

91871d1

verified ·

1 Parent(s): b279ec8

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +69 -0

config.json ADDED Viewed

	@@ -0,0 +1,69 @@

+{
+  "architectures": [
+    "Lfm2MoEForCausalLM"
+  ],
+  "auto_map": {
+    "AutoModelForCausalLM": "modeling_lfm2_moe_final.Lfm2MoEForCausalLM"
+  },
+  "block__name_mlp": "parallel_mlp_merged",
+  "block_auto_adjust_ff_dim": false,
+  "block_dim": 1024,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_ffn_te_autocast": false,
+  "block_ffn_use_quantized_params": false,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_sequence_parallel_norm_across_tp": false,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1024,
+  "conv_use_xavier_init": true,
+  "dtype": "float32",
+  "eos_token_id": 7,
+  "ffn_te_autocast": false,
+  "ffn_use_quantized_params": false,
+  "full_attn_idxs": null,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "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": 16,
+  "num_heads": 16,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization": "int4",
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sequence_parallel_norm_across_tp": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}