Instructions to use LiquidAI/LFM2-700M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LiquidAI/LFM2-700M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LiquidAI/LFM2-700M") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-700M") model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-700M") 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 LiquidAI/LFM2-700M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LiquidAI/LFM2-700M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LiquidAI/LFM2-700M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/LiquidAI/LFM2-700M
- SGLang
How to use LiquidAI/LFM2-700M 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 "LiquidAI/LFM2-700M" \ --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": "LiquidAI/LFM2-700M", "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 "LiquidAI/LFM2-700M" \ --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": "LiquidAI/LFM2-700M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use LiquidAI/LFM2-700M with Docker Model Runner:
docker model run hf.co/LiquidAI/LFM2-700M
Support tool calls
Browse files- chat_template.jinja +49 -4
chat_template.jinja
CHANGED
|
@@ -1,4 +1,49 @@
|
|
| 1 |
-
{{bos_token}}
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{bos_token}}
|
| 2 |
+
{%- if tools %}
|
| 3 |
+
{%- set tool_message = 'List of tools: <|tool_list_start|>' + tools|selectattr('type','eq','function')|map(attribute='function')|list|tojson + '<|tool_list_end|>' %}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
|
| 6 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 7 |
+
{%- set system_message = messages[0]['content'] + ('\n' + tool_message if tool_message else '') %}
|
| 8 |
+
{%- set loop_messages = messages[1:] %}
|
| 9 |
+
{%- else %}
|
| 10 |
+
{%- set system_message = tool_message if tool_message else none %}
|
| 11 |
+
{%- set loop_messages = messages %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
|
| 14 |
+
{{- '<|im_start|>system\n' + system_message + '<|im_end|>\n' if system_message }}
|
| 15 |
+
|
| 16 |
+
{%- for message in loop_messages %}
|
| 17 |
+
{%- set message_content = message['content'] if message['content'] else '' %}
|
| 18 |
+
{{- '<|im_start|>' + message['role'] + '\n' }}
|
| 19 |
+
|
| 20 |
+
{%- if message['role'] == 'assistant' and message['tool_calls'] %}
|
| 21 |
+
{{- '<|tool_call_start|>[' }}
|
| 22 |
+
|
| 23 |
+
{%- for tool_call_function in message['tool_calls']|selectattr('type','eq','function')|map(attribute='function')|list %}
|
| 24 |
+
{{- tool_call_function['name'] + '(' }}
|
| 25 |
+
|
| 26 |
+
{%- for k, v in tool_call_function['arguments'].items() %}
|
| 27 |
+
{{- k + '=' + v|tojson }}
|
| 28 |
+
|
| 29 |
+
{%- if not loop.last %}
|
| 30 |
+
{{- ', ' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- endfor %}
|
| 33 |
+
|
| 34 |
+
{%- if not loop.last %}
|
| 35 |
+
{{- '), ' }}
|
| 36 |
+
{%- else %}
|
| 37 |
+
{{- ')' }}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- endfor %}
|
| 40 |
+
|
| 41 |
+
{{- ']<|tool_call_end|>' }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
|
| 44 |
+
{{- message_content + '<|im_end|>\n' }}
|
| 45 |
+
{%- endfor %}
|
| 46 |
+
|
| 47 |
+
{%- if add_generation_prompt %}
|
| 48 |
+
{{- '<|im_start|>assistant\n' }}
|
| 49 |
+
{%- endif %}
|