Instructions to use eadx/LFM2.5-8B-A1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eadx/LFM2.5-8B-A1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eadx/LFM2.5-8B-A1B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("eadx/LFM2.5-8B-A1B") model = AutoModelForCausalLM.from_pretrained("eadx/LFM2.5-8B-A1B") 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 eadx/LFM2.5-8B-A1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "eadx/LFM2.5-8B-A1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eadx/LFM2.5-8B-A1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/eadx/LFM2.5-8B-A1B
- SGLang
How to use eadx/LFM2.5-8B-A1B 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 "eadx/LFM2.5-8B-A1B" \ --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": "eadx/LFM2.5-8B-A1B", "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 "eadx/LFM2.5-8B-A1B" \ --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": "eadx/LFM2.5-8B-A1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use eadx/LFM2.5-8B-A1B with Docker Model Runner:
docker model run hf.co/eadx/LFM2.5-8B-A1B
File size: 4,621 Bytes
94182a9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | {{- bos_token -}}
{%- set preserve_thinking = preserve_thinking | default(false) -%}
{%- macro format_arg_value(arg_value) -%}
{%- if arg_value is string -%}
{{- "'" + arg_value + "'" -}}
{%- elif arg_value is mapping -%}
{{- arg_value | tojson -}}
{%- else -%}
{{- arg_value | string -}}
{%- endif -%}
{%- endmacro -%}
{%- macro parse_content(content) -%}
{%- if content is string -%}
{{- content -}}
{%- else -%}
{%- set _ns = namespace(result="") -%}
{%- for item in content -%}
{%- if item["type"] == "image" -%}
{%- set _ns.result = _ns.result + "<image>" -%}
{%- elif item["type"] == "text" -%}
{%- set _ns.result = _ns.result + item["text"] -%}
{%- else -%}
{%- set _ns.result = _ns.result + item | tojson -%}
{%- endif -%}
{%- endfor -%}
{{- _ns.result -}}
{%- endif -%}
{%- endmacro -%}
{%- macro render_tool_calls(tool_calls) -%}
{%- set tool_calls_ns = namespace(tool_calls=[]) -%}
{%- for tool_call in tool_calls -%}
{%- set func_name = tool_call["function"]["name"] -%}
{%- set func_args = tool_call["function"]["arguments"] -%}
{%- set args_ns = namespace(arg_strings=[]) -%}
{%- for arg_name, arg_value in func_args.items() -%}
{%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
{%- endfor -%}
{%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
{%- endfor -%}
{{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
{%- endmacro -%}
{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
{%- if messages[0]["role"] == "system" -%}
{%- if messages[0].get("content") -%}
{%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
{%- endif -%}
{%- set messages = messages[1:] -%}
{%- endif -%}
{%- if tools -%}
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
{%- for tool in tools -%}
{%- if tool is not string -%}
{%- set tool = tool | tojson -%}
{%- endif -%}
{%- set ns.system_prompt = ns.system_prompt + tool -%}
{%- if not loop.last -%}
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
{%- endif -%}
{%- endfor -%}
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
{%- endif -%}
{%- if ns.system_prompt -%}
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
{%- endif -%}
{%- for message in messages -%}
{%- if message["role"] == "user" -%}
{%- set ns.last_user_index = loop.index0 -%}
{%- endif -%}
{%- endfor -%}
{%- for message in messages -%}
{{- "<|im_start|>" + message.role + "\n" -}}
{%- if message.role == "assistant" -%}
{%- generation -%}
{%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
{{- "<think>" + message.thinking + "</think>" -}}
{%- endif -%}
{%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
{%- set _has_cfm = false -%}
{%- if message.content is defined -%}
{%- set content = parse_content(message.content) -%}
{%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
{%- if "</think>" in content -%}
{%- set content = content.split("</think>")[-1] | trim -%}
{%- endif -%}
{%- endif -%}
{%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
{%- set _has_cfm = true -%}
{%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
{{- content[:_trunc_len] -}}
{%- else -%}
{{- content -}}
{%- endif -%}
{%- endif -%}
{%- if message.tool_calls is defined -%}
{{- render_tool_calls(message.tool_calls) -}}
{%- endif -%}
{%- if _has_cfm -%}
{{- _cfm_tag -}}
{%- endif -%}
{{- "<|im_end|>\n" -}}
{%- endgeneration -%}
{%- else %}
{%- if message.get("content") -%}
{{- parse_content(message["content"]) -}}
{%- endif -%}
{{- "<|im_end|>\n" -}}
{%- endif %}
{%- endfor -%}
{%- if add_generation_prompt -%}
{{- "<|im_start|>assistant\n" -}}
{%- endif -%} |