LFM2-2.6B-ONNX

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
What is C. elegans?<|im_end|>
<|im_start|>assistant
It's a tiny nematode that lives in temperate soil environments.<|im_end|>

<|startoftext|><|im_start|>system
List of tools: <|tool_list_start|>[{"name": "get_candidate_status", "description": "Retrieves the current status of a candidate in the recruitment process", "parameters": {"type": "object", "properties": {"candidate_id": {"type": "string", "description": "Unique identifier for the candidate"}}, "required": ["candidate_id"]}}]<|tool_list_end|><|im_end|>
<|im_start|>user
What is the current status of candidate ID 12345?<|im_end|>
<|im_start|>assistant
<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
<|im_start|>tool
<|tool_response_start|>{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}<|tool_response_end|><|im_end|>
<|im_start|>assistant
The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>

npm i @huggingface/transformers

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/LFM2-2.6B-ONNX",
  { dtype: "q4" },
);

// 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.

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

// Load tokenizer and model
const model_id = "onnx-community/LFM2-2.6B-ONNX";
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const model = await AutoModelForCausalLM.from_pretrained(
  model_id, { dtype: "q4", device: "webgpu" },
);

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

// Prepare inputs
const input = tokenizer.apply_chat_template(messages, {
  tools,
  add_generation_prompt: true,
  return_dict: true,
});

// Generate output
const sequences = await model.generate({
  ...input,
  max_new_tokens: 512,
  do_sample: false,
  streamer: new TextStreamer(tokenizer, { skip_prompt: true, skip_special_tokens: false }),
});

// Decode and print the generated text
const response = tokenizer.batch_decode(
  sequences.slice(null, [input.input_ids.dims[1], null]),
  { skip_special_tokens: true },
);
console.log(response[0]); // [get_weather(location="New York", unit="fahrenheit")]

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

# 1. Load config, processor, and model
model_id = "onnx-community/LFM2-2.6B-ONNX"
config = AutoConfig.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
filename = "model_q4.onnx" # Options: "model.onnx", "model_fp16.onnx", "model_q4.onnx", "model_q4f16.onnx"
model_path = hf_hub_download(repo_id=model_id, filename=f"onnx/{filename}") # Download the graph
hf_hub_download(repo_id=model_id, filename=f"onnx/{filename}_data") # Download the weights
session = onnxruntime.InferenceSession(model_path)

## Set config values
num_key_value_heads = config.num_key_value_heads
head_dim = config.hidden_size // config.num_attention_heads
num_hidden_layers = config.num_hidden_layers
eos_token_id = config.eos_token_id
hidden_size = config.hidden_size
conv_L_cache = config.conv_L_cache
layer_types = config.layer_types

# 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]
position_ids = np.tile(np.arange(0, input_ids.shape[-1]), (batch_size, 1))
past_cache_values = {}
for i in range(num_hidden_layers):
  if layer_types[i] == 'full_attention':
    for kv in ('key', 'value'):
      past_cache_values[f'past_key_values.{i}.{kv}'] = np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
  elif layer_types[i] == 'conv':
    past_cache_values[f'past_conv.{i}'] = np.zeros([batch_size, hidden_size, conv_L_cache], dtype=np.float32)
  else:
    raise ValueError(f"Unsupported layer type: {layer_types[i]}")

# 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,
      position_ids=position_ids,
      **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)
  position_ids = position_ids[:, -1:] + 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 (input_ids == eos_token_id).all():
    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])