LFM2-350M-ONNX

npm i @huggingface/transformers

import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/LFM2-350M-ONNX",
  { dtype: "q4", device: "webgpu" },
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What is the capital of France?" },
];

// Generate a response
const output = await generator(messages, {
    max_new_tokens: 512,
    do_sample: false,
    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true }),
});
console.log(output[0].generated_text.at(-1).content);
// The capital of France is Paris. It is a vibrant city known for its historical landmarks, art, fashion, and cuisine.

import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/LFM2-350M-ONNX",
  { dtype: "q4", device: "webgpu" },
);

// Define the tools available to the model
const tools = [
  {
    name: "get_weather",
    description: "Get current weather information for a location",
    parameters: {
      type: "object",
      properties: {
        location: {
          type: "string",
          description: "The city and state, e.g. San Francisco, CA",
        },
        unit: {
          type: "string",
          enum: ["celsius", "fahrenheit"],
          description: "The unit of temperature to use",
        },
      },
      required: ["location"],
    },
  },
];

// Define the list of messages
const messages = [
  { role: "user", content: "What's the weather like in New York?" },
];

// Generate a response
const output = await generator(messages, {
    max_new_tokens: 512,
    do_sample: false,
    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true }),
    tokenizer_encode_kwargs: { tools },
});
console.log(output[0].generated_text.at(-1).content);
// [get_weather(location="New York, NY", unit="fahrenheit")]

from transformers import AutoConfig, AutoTokenizer
import onnxruntime
import numpy as np
from huggingface_hub import snapshot_download

# 1. Load config, processor, and model
model_id = "onnx-community/LFM2-350M-ONNX"
config = AutoConfig.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
eos_token_id = config.eos_token_id

filename = "model.onnx" # Options: "model.onnx", "model_fp16.onnx", "model_q4.onnx", "model_q4f16.onnx"
model_path = snapshot_download(repo_id=model_id, allow_patterns=f"onnx/{filename}*") # Download the graph + weights
session = onnxruntime.InferenceSession(f"{model_path}/onnx/{filename}")

# 2. Prepare inputs
prompt = "What is C. elegans?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="np")
input_ids = inputs['input_ids']
attention_mask = inputs['attention_mask']
batch_size = input_ids.shape[0]
num_logits_to_keep = np.array(1, dtype=np.int64)

past_cache_values = {}
for inp in session.get_inputs():
    name = inp.name
    shape = inp.shape
    dtype = np.float32 if inp.type == "tensor(float)" else np.float16
    if name.startswith("past_key_values"):
        # Attention KV cache: shape [batch_size, num_kv_heads, 0, head_dim]
        past_cache_values[name] = np.zeros([batch_size, shape[1], 0, shape[3]], dtype=dtype)
    elif name.startswith("past_conv"):
        # Conv cache: shape [batch_size, hidden_size, conv_L_cache]
        past_cache_values[name] = np.zeros([batch_size, shape[1], shape[2]], dtype=dtype)

# 3. Generation loop
max_new_tokens = 1024
generated_tokens = np.array([[]], dtype=np.int64)
for i in range(max_new_tokens):
  logits, *present_cache_values = session.run(None, dict(
      input_ids=input_ids,
      attention_mask=attention_mask,
      num_logits_to_keep=num_logits_to_keep,
      **past_cache_values,
  ))

  ## Update values for next generation loop
  input_ids = logits[:, -1].argmax(-1, keepdims=True)
  attention_mask = np.concatenate([attention_mask, np.ones_like(input_ids, dtype=np.int64)], axis=-1)
  for j, key in enumerate(past_cache_values):
    past_cache_values[key] = present_cache_values[j]
  generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
  if np.isin(input_ids, eos_token_id).any():
      break

  ## (Optional) Streaming
  print(tokenizer.decode(input_ids[0]), end='', flush=True)
print()

# 4. Output result
print(tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0])