Add support for ERNIE-4.5 #1354
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
kunal-vaishnavi
added a commit
to microsoft/onnxruntime-genai
that referenced
this pull request
Jul 7, 2025
Enables exporting the new Ernie 4.5 models via onnxruntime-genai: https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT I've uploaded the converted model to https://huggingface.co/onnx-community/ERNIE-4.5-0.3B-ONNX. Currently only supports the non-MoE version... but maybe someone can help with the MoE version: https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT --- Models tested and validated with python ort & [transformers.js](huggingface/transformers.js#1354): ```py from transformers import AutoConfig, AutoTokenizer import onnxruntime import numpy as np # 1. Load config, processor, and model path_to_model = "./path/to/model" config = AutoConfig.from_pretrained("baidu/ERNIE-4.5-0.3B-PT", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("baidu/ERNIE-4.5-0.3B-PT", trust_remote_code=True) decoder_session = onnxruntime.InferenceSession(f"{path_to_model}/model.onnx") ## Set config values num_key_value_heads = config.num_key_value_heads head_dim = config.head_dim num_hidden_layers = config.num_hidden_layers eos_token_id = config.eos_token_id # 2. Prepare inputs ## Create input messages messages = [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Write me a poem about Machine Learning." }, ] ## Apply tokenizer inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="np") ## Prepare decoder inputs batch_size = inputs['input_ids'].shape[0] past_key_values = { f'past_key_values.{layer}.{kv}': np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32) for layer in range(num_hidden_layers) for kv in ('key', 'value') } input_ids = inputs['input_ids'] position_ids = np.tile(np.arange(1, input_ids.shape[-1] + 1), (batch_size, 1)) attention_mask = np.ones_like(input_ids, dtype=np.int64) # 3. Generation loop max_new_tokens = 1024 generated_tokens = np.array([[]], dtype=np.int64) for i in range(max_new_tokens): logits, *present_key_values = decoder_session.run(None, dict( input_ids=input_ids, attention_mask=attention_mask, position_ids=position_ids, **past_key_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_key_values): past_key_values[key] = present_key_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)) ``` --------- Co-authored-by: kunal-vaishnavi <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Original model: https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT
ONNX weights: https://huggingface.co/onnx-community/ERNIE-4.5-0.3B-ONNX