Instructions to use onnx-internal-testing/tiny-random-Lfm2ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onnx-internal-testing/tiny-random-Lfm2ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="onnx-internal-testing/tiny-random-Lfm2ForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("onnx-internal-testing/tiny-random-Lfm2ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("onnx-internal-testing/tiny-random-Lfm2ForCausalLM")
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

vLLM

How to use onnx-internal-testing/tiny-random-Lfm2ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "onnx-internal-testing/tiny-random-Lfm2ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnx-internal-testing/tiny-random-Lfm2ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/onnx-internal-testing/tiny-random-Lfm2ForCausalLM

SGLang

How to use onnx-internal-testing/tiny-random-Lfm2ForCausalLM 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 "onnx-internal-testing/tiny-random-Lfm2ForCausalLM" \
    --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": "onnx-internal-testing/tiny-random-Lfm2ForCausalLM",
		"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 "onnx-internal-testing/tiny-random-Lfm2ForCausalLM" \
        --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": "onnx-internal-testing/tiny-random-Lfm2ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use onnx-internal-testing/tiny-random-Lfm2ForCausalLM with Docker Model Runner:
```
docker model run hf.co/onnx-internal-testing/tiny-random-Lfm2ForCausalLM
```

Xenova HF Staff commited on Jul 16, 2025

Commit

76ac851

verified ·

1 Parent(s): d5dfe90

Upload folder using huggingface_hub

Browse files

Files changed (12) hide show

.gitattributes +4 -0
config.json +10 -3
onnx/model.onnx +3 -0
onnx/model.onnx_data +3 -0
onnx/model_fp16.onnx +3 -0
onnx/model_fp16.onnx_data +3 -0
onnx/model_q4.onnx +3 -0
onnx/model_q4.onnx_data +3 -0
onnx/model_q4f16.onnx +3 -0
onnx/model_q4f16.onnx_data +3 -0
tokenizer.json +0 -0
tokenizer_config.json +3 -2

.gitattributes CHANGED Viewed

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "eos_token_id": 7,
   "hidden_size": 32,
   "initializer_range": 0.02,
-  "intermediate_size": 32,
   "layer_types": [
     "full_attention",
     "conv"
@@ -39,5 +39,12 @@
   "transformers_version": "4.54.0.dev0",
   "use_cache": true,
   "use_pos_enc": true,
-  "vocab_size": 65536
-}

   "eos_token_id": 7,
   "hidden_size": 32,
   "initializer_range": 0.02,
+  "intermediate_size": 256,
   "layer_types": [
     "full_attention",
     "conv"
   "transformers_version": "4.54.0.dev0",
   "use_cache": true,
   "use_pos_enc": true,
+  "vocab_size": 65536,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    },
+    "use_external_data_format": true
+  }
+}

onnx/model.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3153b565008d69db4c17d69c7085c1c201cc3d035b4e5a11876bf9e105538274
+size 22935

onnx/model.onnx_data ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc57fe8512eb2d33e79bfa15272921a99db97a05487d00ea0ae8a235f629bff
+size 12845056

onnx/model_fp16.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:000f9bb76f06d9dd59fd6c70cc6ade5dacf954f52fe5709cd2683e536c98b947
+size 23198

onnx/model_fp16.onnx_data ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c347a0906feb282a182a3ca61f6a045d43975f98b54b72582a1fbd1002898336
+size 6356992

onnx/model_q4.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8586910623ac41844751cd63b5f3a1c18539545857949f721a3bc3a7564a1e05
+size 27175

onnx/model_q4.onnx_data ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b49e6af9a2ec163175946388477f2b3c131be92ee6c82967c083e30252aec280
+size 12648448

onnx/model_q4f16.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4e1f11cf46a472b558817d63777d670482ef334b3e8fe9dfba274eb81eca0c
+size 27419

onnx/model_q4f16.onnx_data ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:11b3d5608904a3e4886b31cda6529efa0a4d3681182489cb22b6ad2cc40dee70
+size 6291456

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -4070,5 +4070,6 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "use_default_system_prompt": false,
-  "use_fast": true
-}

   "spaces_between_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "use_default_system_prompt": false,
+  "use_fast": true,
+  "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}