初始化项目，由ModelHub XC社区提供模型

Model: Norod78/distilgpt2-base-pretrained-he Source: Original Platform
2026-07-31 19:45:18 +08:00
commit 869ee920c0
26 changed files with 151127 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,20 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.onnx filter=lfs diff=lfs merge=lfs -text
+tf_model.h5 filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,2 @@
+
+
--- a/README.md
+++ b/README.md
@@ -0,0 +1,67 @@
+---
+language: he
+
+thumbnail: https://avatars1.githubusercontent.com/u/3617152?norod.jpg
+widget:
+- text: "האיש האחרון עלי אדמות ישב לבד בחדרו כשלפתע נשמעה נקישה"
+- text: "שלום, קרואים לי"
+- text: "הארי פוטר חייך חיוך נבוך"
+- text: "החתול שלך מאוד חמוד ו"
+
+license: mit
+---
+
+# distilgpt2-base-pretrained-he
+
+A tiny GPT2 based Hebrew text generation model initially trained on a TPUv3-8 which was made avilable to me via the [TPU Research Cloud](https://sites.research.google/trc/) Program. Then was further fine-tuned on GPU.
+
+## Dataset
+
+### oscar (unshuffled deduplicated he) - [Homepage](https://oscar-corpus.com) | [Dataset Permalink](https://huggingface.co/datasets/viewer/?dataset=oscar&config=unshuffled_deduplicated_he)
+
+The Open Super-large Crawled ALMAnaCH coRpus is a huge multilingual corpus obtained by language classification and filtering of the Common Crawl corpus using the goclassy architecture.
+
+### CC-100 (he) - [HomePage](https://data.statmt.org/cc-100/)
+
+This corpus comprises of monolingual data for 100+ languages and also includes data for romanized languages. This was constructed using the urls and paragraph indices provided by the CC-Net repository by processing January-December 2018 Commoncrawl snapshots. Each file comprises of documents separated by double-newlines and paragraphs within the same document separated by a newline. The data is generated using the open source CC-Net repository.
+
+### Misc
+* Hebrew Twitter
+* Wikipedia
+* Various other sources
+
+## Training
+
+* Done on a TPUv3-8 VM using [Huggingface's clm-flax example script](https://github.com/huggingface/transformers/blob/master/examples/flax/language-modeling/run_clm_flax.py) <BR>
+* I have made a list of items which might make it easier for other to use this script. The list was posted to [This discussion forum](https://discuss.huggingface.co/t/ideas-for-beginner-friendlier-tpu-vm-clm-training/8351)
+* Further training was performed on GPU
+
+## Usage
+
+
+#### Simple usage sample code
+
+```python
+
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+def main():
+    model_name="Norod78/distilgpt2-base-pretrained-he"
+
+    prompt_text = "שלום, קוראים לי"
+    generated_max_length = 192
+
+    print("Loading model...")
+    model =  AutoModelForCausalLM.from_pretrained(model_name)
+    print('Loading Tokenizer...')
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    text_generator = pipeline(task="text-generation", model=model, tokenizer=tokenizer)
+
+    print("Generating text...")
+    result = text_generator(prompt_text, num_return_sequences=1, batch_size=1, do_sample=True, top_k=40, top_p=0.92, temperature = 1, repetition_penalty=5.0, max_length = generated_max_length)
+
+    print("result = " + str(result))
+
+if __name__ == '__main__':
+    main()
+```
--- a/config.json
+++ b/config.json
@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "./hebrew-distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": 50257,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}
--- a/converters/convert2coreml.py
+++ b/converters/convert2coreml.py
@@ -0,0 +1,439 @@
+"""
+Recreate the Core ML model from scratch using
+coremltools' neural_network.NeuralNetworkBuilder
+"""
+import coremltools
+import coremltools.models.datatypes as datatypes
+from coremltools.models import neural_network as neural_network
+from coremltools.models.utils import save_spec
+import numpy as np
+
+# get weights
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+model_name = "./distilgpt2-base-pretrained-he"
+save_directory = "tmp/coreml/"
+#!mkdir -p $save_directory
+file_name = "model.mlmodel"
+
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+lm_head_model = GPT2LMHeadModel.from_pretrained(model_name).eval()
+model = lm_head_model.transformer
+
+wte = model.wte.weight.data.numpy().transpose() # shape (768, 50257) /!\ i hate this
+wpe = model.wpe.weight.data.numpy().transpose() # shape (768, 1024)
+
+sequence_length = 64
+steps = 6
+
+# build model
+input_features = [
+	('input_ids', datatypes.Array(sequence_length)),
+	('position_ids', datatypes.Array(sequence_length)),
+]
+output_features = [('output_logits', None)]
+
+builder = neural_network.NeuralNetworkBuilder(
+	input_features,
+	output_features,
+	mode=None,
+	disable_rank5_shape_mapping=True,
+)
+builder.add_expand_dims(
+	name='input_ids_expanded_to_rank5',
+	input_name='input_ids',
+	output_name='input_ids_expanded_to_rank5',
+	axes=(1, 2, 3, 4)
+)
+builder.add_expand_dims(
+	name='position_ids_expanded_to_rank5',
+	input_name='position_ids',
+	output_name='position_ids_expanded_to_rank5',
+	axes=(1, 2, 3, 4)
+)
+builder.add_embedding(
+	name='token_embeddings',
+	input_name='input_ids_expanded_to_rank5',
+	output_name='token_embeddings',
+	W=wte,
+	b=None,
+	input_dim=50257,
+	output_channels=768,
+	has_bias=False,
+)
+builder.add_embedding(
+	name='positional_embeddings',
+	input_name='position_ids_expanded_to_rank5',
+	output_name='positional_embeddings',
+	W=wpe,
+	b=None,
+	input_dim=1024,
+	output_channels=768,
+	has_bias=False,
+)
+
+# Input:, Output: (seq, 1, 768, 1, 1)
+builder.add_add_broadcastable(
+	name='embeddings_addition',
+	input_names=['token_embeddings', 'positional_embeddings'],
+	output_name=f'{0}_previous_block'
+)
+
+for i in range(steps):
+	print(i)
+	ln_weight = model.h[i].ln_1.weight.data.numpy().reshape((1, 1, 768, 1, 1))
+	ln_bias = model.h[i].ln_1.bias.data.numpy().reshape((1, 1, 768, 1, 1))
+	ln_epsilon = model.h[i].ln_1.eps
+
+	builder.add_mvn(
+		name=f"{i}_block_ln_1",
+		input_name=f"{i}_previous_block",
+		# output_name=f"{i}_block_ln_1_output",
+		output_name=f"{i}_block_ln_1",
+		across_channels=True,
+		normalize_variance=True,
+		epsilon=ln_epsilon
+	)
+
+	builder.add_scale(
+		name=f"{i}_block_ln_1_scaled",
+		input_name=f"{i}_block_ln_1",
+		output_name=f"{i}_block_ln_1_scaled",
+		W=ln_weight,
+		b=ln_bias,
+		has_bias=True,
+		shape_scale=[768],
+		shape_bias=[768]
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_ln_1_reshape",
+		input_name=f"{i}_block_ln_1_scaled",
+		output_name=f"{i}_block_ln_1_scaled_transposed",
+		axes=(1, 0, 2, 3, 4)
+	)
+
+
+	conv_1D_bias = model.h[i].attn.c_attn.bias.data.numpy().reshape((1, 1, 2304, 1, 1))
+	conv_1D_weights = model.h[i].attn.c_attn.weight.data.numpy().transpose().reshape((1, 768, 2304, 1, 1))
+
+	builder.add_inner_product(
+		name=f"{i}_block_attn_conv",
+		input_name=f"{i}_block_ln_1_scaled_transposed",
+		output_name=f"{i}_block_attn_conv",
+		input_channels=768,
+		output_channels=2304,
+		W=conv_1D_weights,
+		b=conv_1D_bias,
+		has_bias=True
+	)
+
+	builder.add_split(
+		name=f"{i}_block_attn_qkv_split",
+		input_name=f"{i}_block_attn_conv",
+		output_names=[f"{i}_block_attn_q", f"{i}_block_attn_k", f"{i}_block_attn_v"]
+	)
+
+	builder.add_rank_preserving_reshape(
+		name=f"{i}_block_attn_q_reshape",
+		input_name=f"{i}_block_attn_q",
+		output_name=f"{i}_block_attn_q_reshape",
+		output_shape=(1, 1, sequence_length, 12, 64)
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_attn_q_reshape_permuted",
+		input_name=f"{i}_block_attn_q_reshape",
+		output_name=f"{i}_block_attn_q_reshape_permuted",
+		axes=(0, 1, 3, 2, 4)
+	)
+
+	builder.add_rank_preserving_reshape(
+		name=f"{i}_block_attn_k_reshape",
+		input_name=f"{i}_block_attn_k",
+		output_name=f"{i}_block_attn_k_reshape",
+		output_shape=(1, 1, sequence_length, 12, 64)
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_attn_k_reshape_permuted",
+		input_name=f"{i}_block_attn_k_reshape",
+		output_name=f"{i}_block_attn_k_reshape_permuted",
+		axes=(0, 1, 3, 4, 2)
+	)
+
+	builder.add_rank_preserving_reshape(
+		name=f"{i}_block_attn_v_reshape",
+		input_name=f"{i}_block_attn_v",
+		output_name=f"{i}_block_attn_v_reshape",
+		output_shape=(1, 1, sequence_length, 12, 64)
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_attn_v_reshape_permuted",
+		input_name=f"{i}_block_attn_v_reshape",
+		output_name=f"{i}_block_attn_v_reshape_permuted",
+		axes=(0, 1, 3, 2, 4)
+	)
+
+	builder.add_batched_mat_mul(
+		name=f"{i}_block_attn_qv_matmul",
+		input_names=[f"{i}_block_attn_q_reshape_permuted", f"{i}_block_attn_k_reshape_permuted"],
+		output_name=f"{i}_block_attn_qv_matmul"
+	)
+
+	builder.add_scale(
+		name=f"{i}_block_attn_qv_matmul_scaled",
+		input_name=f"{i}_block_attn_qv_matmul",
+		output_name=f"{i}_block_attn_qv_matmul_scaled",
+		W=np.array(1/8),
+		b=0,
+		has_bias=False
+	)
+
+	bias_0 = model.h[i].attn.bias
+	nd = ns = sequence_length
+	b = (model.h[i].attn.bias[:, :, ns-nd:ns, :ns]).unsqueeze(0)
+
+	builder.add_scale(
+		name=f"{i}_block_attn_bias",
+		input_name=f"{i}_block_attn_qv_matmul_scaled",
+		output_name=f"{i}_block_attn_bias",
+		W=b,
+		b=None,
+		has_bias=False,
+		shape_scale=[1, sequence_length, sequence_length]
+	)
+
+	bias_constant_0 = - 1e4 * (1 - b)
+
+	builder.add_bias(
+		name=f"{i}_block_attn_afterbias",
+		input_name=f"{i}_block_attn_bias",
+		output_name=f"{i}_block_attn_afterbias",
+		# output_name=f"output_logits",
+		b=bias_constant_0,
+		shape_bias=[1, sequence_length, sequence_length],
+	)
+
+	builder.add_squeeze(
+		name=f"{i}_squeezit",
+		input_name=f"{i}_block_attn_afterbias",
+		output_name=f"{i}_squeezit",
+		axes=[0, 1]
+	)
+
+	builder.add_softmax(
+		name=f"{i}_block_attn_softmax",
+		input_name=f"{i}_squeezit",
+		output_name=f"{i}_block_attn_softmax",
+	)
+
+	builder.add_expand_dims(
+		name=f"{i}_expandit",
+		input_name=f"{i}_block_attn_softmax",
+		output_name=f"{i}_expandit",
+		axes=[0, 1]
+	)
+
+	builder.add_batched_mat_mul(
+		name=f"{i}_block_full_attention",
+		input_names=[f"{i}_expandit", f"{i}_block_attn_v_reshape_permuted"],
+		output_name=f"{i}_block_full_attention"
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_full_attention_merged_t",
+		input_name=f"{i}_block_full_attention",
+		output_name=f"{i}_block_full_attention_merged_t",
+		axes=[0, 1, 3, 2, 4]
+	)
+
+	builder.add_rank_preserving_reshape(
+		name=f"{i}_block_full_attention_merged",
+		input_name=f"{i}_block_full_attention_merged_t",
+		output_name=f"{i}_block_full_attention_merged",
+		output_shape=[1, 1, 1, sequence_length, 768]
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_attn_conv_proj_t",
+		input_name=f"{i}_block_full_attention_merged",
+		output_name=f"{i}_block_attn_conv_proj_t",
+		axes=[0, 3, 4, 1, 2]
+	)
+
+	conv_1D_proj_bias = model.h[i].attn.c_proj.bias.data.numpy().reshape((1, 1, 768, 1, 1))
+	conv_1D_proj_weights = model.h[i].attn.c_proj.weight.data.numpy().transpose().reshape((1, 768, 768, 1, 1))
+
+	# Input:, Output: (1, 3, 768, 1, 1)
+	builder.add_inner_product(
+		name=f"{i}_block_attn_conv_proj",
+		input_name=f"{i}_block_attn_conv_proj_t",
+		output_name=f"{i}_block_attn_conv_proj",
+		input_channels=768,
+		output_channels=768,
+		W=conv_1D_proj_weights,
+		b=conv_1D_proj_bias,
+		has_bias=True
+	)
+
+	# Input: (seq, 1, 768, 1, 1), Output: (1, seq, 768, 1, 1)
+	builder.add_transpose(
+		name=f"{i}_previous_block_t",
+		input_name=f'{i}_previous_block',
+		output_name=f"{i}_previous_block_t",
+		axes=[1, 0, 2, 3, 4]
+	)
+
+	# Input: [(1, seq, 768, 1, 1), (1, seq, 768, 1, 1)], Output: (1, seq, 768, 1, 1)
+	builder.add_add_broadcastable(
+		name=f"{i}_block_xa_sum",
+		input_names=[f"{i}_previous_block_t", f"{i}_block_attn_conv_proj"],
+		output_name=f"{i}_block_xa_sum",
+		# output_name=f"output_logits"
+	)
+
+	ln_2_weight = model.h[i].ln_2.weight.data.numpy().reshape((1, 1, 768, 1, 1))
+	ln_2_bias = model.h[i].ln_2.bias.data.numpy().reshape((1, 1, 768, 1, 1))
+	ln_2_epsilon = model.h[i].ln_2.eps
+
+	# Input: (1, seq, 768, 1, 1), Output:
+	builder.add_mvn(
+		name=f"{i}_block_ln_2",
+		input_name=f"{i}_block_xa_sum",
+		output_name=f"{i}_block_ln_2",
+		across_channels=True,
+		normalize_variance=True,
+		epsilon=ln_2_epsilon
+	)
+
+	builder.add_scale(
+		name=f"{i}_block_ln_2_scaled",
+		input_name=f"{i}_block_ln_2",
+		# output_name=f"output_logits",
+		output_name=f"{i}_block_ln_2_scaled",
+		W=ln_2_weight,
+		b=ln_2_bias,
+		has_bias=True,
+		shape_scale=[768],
+		shape_bias=[768]
+	)
+
+	mlp_conv_1D_fc_bias = model.h[i].mlp.c_fc.bias.data.numpy().reshape((1, 1, 3072, 1, 1))
+	mlp_conv_1D_fc_weights = model.h[i].mlp.c_fc.weight.data.numpy().transpose().reshape((1, 768, 3072, 1, 1))
+
+	# Input:, Output: (1, 3, 3072, 1, 1)
+	builder.add_inner_product(
+		name=f"{i}_block_mlp_conv_fc",
+		input_name=f"{i}_block_ln_2_scaled",
+		output_name=f"{i}_block_mlp_conv_fc",
+		# output_name=f"output_logits",
+		input_channels=768,
+		output_channels=3072,
+		W=mlp_conv_1D_fc_weights,
+		b=mlp_conv_1D_fc_bias,
+		has_bias=True
+	)
+
+	builder.add_gelu(
+		name=f"{i}_block_mlp_gelu",
+		input_name=f"{i}_block_mlp_conv_fc",
+		output_name=f"{i}_block_mlp_gelu",
+		# output_name=f"output_logits",
+		mode='TANH_APPROXIMATION'
+	)
+
+	mlp_conv_1D_proj_bias = model.h[i].mlp.c_proj.bias.data.numpy().reshape((1, 1, 768, 1, 1))
+	mlp_conv_1D_proj_weights = model.h[i].mlp.c_proj.weight.data.numpy().transpose().reshape((1, 3072, 768, 1, 1))
+
+	# Input:, Output: (1, 3, 3072, 1, 1)
+	builder.add_inner_product(
+		name=f"{i}_block_mlp_conv_proj",
+		input_name=f"{i}_block_mlp_gelu",
+		output_name=f"{i}_block_mlp_conv_proj",
+		# output_name=f"output_logits",
+		input_channels=3072,
+		output_channels=768,
+		W=mlp_conv_1D_proj_weights,
+		b=mlp_conv_1D_proj_bias,
+		has_bias=True
+	)
+
+	builder.add_add_broadcastable(
+		name=f"{i}_block_xm_sum",
+		input_names=[f"{i}_block_xa_sum", f"{i}_block_mlp_conv_proj"],
+		# output_name=f"output_logits"
+		output_name=f"{i + 1}_previous_block_final"
+	)
+
+	builder.add_transpose(
+		name=f"{i}_block_xm_sum_t",
+		input_name=f"{i + 1}_previous_block_final",
+		output_name=f"{i + 1}_previous_block",
+		axes=[1, 0, 2, 3, 4]
+	)
+
+
+ln_f_weight = model.ln_f.weight.data.numpy().reshape((1, 1, 768, 1, 1))
+ln_f_bias = model.ln_f.bias.data.numpy().reshape((1, 1, 768, 1, 1))
+ln_f_epsilon = model.ln_f.eps
+
+# Input: (1, seq, 768, 1, 1), Output:
+builder.add_mvn(
+	name=f"ln_f",
+	input_name=f"{steps}_previous_block_final",
+	output_name=f"ln_f",
+	# output_name=f"output_logits",
+	across_channels=True,
+	normalize_variance=True,
+	epsilon=ln_f_epsilon
+)
+
+builder.add_scale(
+	name=f"ln_f_scaled",
+	input_name=f"ln_f",
+	output_name=f"ln_f_scaled",
+	# output_name=f"output_logits",
+	W=ln_f_weight,
+	b=ln_f_bias,
+	has_bias=True,
+	shape_scale=[768],
+	shape_bias=[768]
+)
+
+lm_head_weights = lm_head_model.lm_head.weight.data.numpy().reshape((1, 50257, 768, 1, 1))
+
+builder.add_inner_product(
+	name="lm_head",
+	input_name="ln_f_scaled",
+	output_name="output_logits",
+	input_channels=768,
+	output_channels=50257,
+	W=lm_head_weights,
+	b=None,
+	has_bias=False
+)
+
+# compile spec to model
+mlmodel = coremltools.models.MLModel(builder.spec)
+
+#save_spec(builder.spec, f'./{model_name}-{sequence_length}-{steps}.mlmodel')
+save_spec(builder.spec, f'./{save_directory}{file_name}')
+# model = coremltools.models.MLModel('gpt2.mlmodel')
+
+# input_ids = np.zeros(sequence_length)
+# position_ids = np.arange(sequence_length).astype(np.float)
+
+# input_data = {
+# 	'input_ids': input_ids,
+# 	'position_ids': position_ids,
+# }
+
+# predictions = mlmodel.predict(input_data)["output_logits"]
+# equal = np.amax(predictions - mlp_conv_proj.detach().numpy())
+
+# print(predictions)
+
+
+# save_spec(builder.spec, 'gpt2.mlmodel')
--- a/converters/convert2flax.py
+++ b/converters/convert2flax.py
@@ -0,0 +1,24 @@
+import argparse
+import logging
+
+import numpy as np
+import torch
+import os
+from transformers import AutoConfig, FlaxAutoModelForCausalLM
+
+logging.basicConfig(
+    format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
+    datefmt="%m/%d/%Y %H:%M:%S",
+    level=logging.INFO,
+)
+logger = logging.getLogger(__name__)
+
+model_path = "./distilgpt2-base-pretrained-he"
+save_directory = "./tmp/flax/"
+
+config_path = os.path.join(model_path, 'config.json')
+
+# Loading from a PyTorch checkpoint file instead of a TensorFlow model (slower)
+config = AutoConfig.from_pretrained(config_path)
+model = FlaxAutoModelForCausalLM.from_pretrained(model_path, from_pt=True, config=config)
+model.save_pretrained(save_directory)
--- a/converters/convert2onnx.py
+++ b/converters/convert2onnx.py
@@ -0,0 +1,31 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM, AutoModel, AutoConfig
+from transformers.onnx import FeaturesManager, convert, export
+from pathlib import Path
+import os
+
+model_id = "./distilgpt2-base-pretrained-he"
+export_folder = "tmp/onnx/"
+file_name = "model.onnx"
+
+print('Loading tokenizer...')
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+print('Saving tokenizer to ', export_folder)
+tokenizer.save_pretrained(export_folder)
+print('Loading model...')
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+feature= "causal-lm"
+model_kind, model_onnx_config = FeaturesManager.check_supported_model_or_raise(model, feature=feature)
+onnx_config = model_onnx_config(model.config)
+
+print("model_kind = {0}\nonx_config = {1}\n".format(model_kind, onnx_config))
+
+onnx_path = Path(export_folder+file_name)
+
+print('Exporting model to ', onnx_path)
+onnx_inputs, onnx_outputs = export(tokenizer, model, onnx_config, onnx_config.default_onnx_opset, onnx_path)
+print('Done')
--- a/converters/convert2tf.py
+++ b/converters/convert2tf.py
@@ -0,0 +1,21 @@
+# Requires transformers >= 4.21.0;
+# Sampling outputs may differ, depending on your hardware.
+from transformers import AutoTokenizer, TFAutoModelForCausalLM
+
+model_checkpoint = "./distilgpt2-base-pretrained-he"
+save_directory = "tmp/tf/"
+file_name = "tf_model.h5"
+
+tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
+model = TFAutoModelForCausalLM.from_pretrained(model_checkpoint, from_pt=True)
+model.config.pad_token_id = model.config.eos_token_id
+inputs = tokenizer(["צחוקים ושיגועים"], return_tensors="tf")
+
+generated = model.generate(**inputs, do_sample=True, seed=(42, 0))
+print("Sampling output: ", tokenizer.decode(generated[0]))
+
+model.save_pretrained(save_directory, file_name=file_name)
+tokenizer.save_pretrained(save_directory)
+
+# > Sampling output: TensorFlow is a great learning platform for learning about
+# data structure and structure in data science..
--- a/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/.gitattributes
+++ b/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/.gitattributes
@@ -0,0 +1 @@
+model.mlmodel filter=lfs diff=lfs merge=lfs -text
--- a/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json
+++ b/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/FeatureDescriptions.json
@@ -0,0 +1,18 @@
+{
+  "Outputs" : {
+    "output_logits" : {
+      "MLFeatureShortDescription" : "--"
+    }
+  },
+  "Inputs" : {
+    "position_ids" : {
+      "MLFeatureShortDescription" : "--"
+    },
+    "input_ids" : {
+      "MLFeatureShortDescription" : "--"
+    }
+  },
+  "TrainingInputs" : {
+
+  }
+}
--- a/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/Metadata.json
+++ b/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/Metadata.json
@@ -0,0 +1,9 @@
+{
+  "MLModelVersionStringKey" : "1.01",
+  "MLModelDescriptionKey" : "hebrew-distilgpt2\n\nA tiny GPT2 based Hebrew text generation model trained on a TPUv3-8 via the TPU Research Cloud Program.",
+  "MLModelCreatorDefinedKey" : {
+    "model_card_url" : "https:\/\/huggingface.co\/Norod78\/distilgpt2-base-pretrained-he"
+  },
+  "MLModelAuthorKey" : "Doron Adler",
+  "MLModelLicenseKey" : "mit"
+}
--- a/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/model.mlmodel
+++ b/distilgpt2-base-pretrained-he.mlpackage/Data/com.apple.CoreML/model.mlmodel
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6a01312efcdb9026f68a3b019e9afe9a15f19ba588db23ae97c6024ad09ad7
+size 482254328
--- a/distilgpt2-base-pretrained-he.mlpackage/Manifest.json
+++ b/distilgpt2-base-pretrained-he.mlpackage/Manifest.json
@@ -0,0 +1,24 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "5CA8030A-3376-40B9-9F77-FE7151EBE0F7": {
+            "author": "com.apple.CoreML",
+            "description": "External FeatureDescription Overlay",
+            "name": "FeatureDescriptions.json",
+            "path": "com.apple.CoreML/FeatureDescriptions.json"
+        },
+        "5EFA4247-BC5C-47CE-9E64-F1747845A076": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "63DB2BDF-B3FD-4CE4-9251-66F29CF34545": {
+            "author": "com.apple.CoreML",
+            "description": "External Metadata Overlay",
+            "name": "Metadata.json",
+            "path": "com.apple.CoreML/Metadata.json"
+        }
+    },
+    "rootModelIdentifier": "5EFA4247-BC5C-47CE-9E64-F1747845A076"
+}
--- a/examples/example-onnx-infer.py
+++ b/examples/example-onnx-infer.py
@@ -0,0 +1,30 @@
+
+#Tested with the following Python package versions:
+#optimum                            1.2.3.dev0
+#transformers                       4.21.0.dev0
+#tokenizers                         0.11.6
+
+from transformers import AutoTokenizer
+from optimum.onnxruntime import ORTModelForCausalLM
+from optimum.pipelines import pipeline
+
+
+def main():
+    model_name="Norod78/distilgpt2-base-pretrained-he"
+
+    prompt_text = "שלום, קוראים לי"
+    generated_max_length = 192
+
+    print("Loading model...")
+    model =  ORTModelForCausalLM.from_pretrained(model_name)
+    print('Loading Tokenizer...')
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    text_generator = pipeline(task="text-generation", model=model, tokenizer=tokenizer)
+
+    print("Generating text...")
+    result = text_generator(prompt_text, num_return_sequences=1, batch_size=1, do_sample=True, top_k=40, top_p=0.92, temperature = 1, repetition_penalty=5.0, max_length = generated_max_length)
+
+    print("result = " + str(result))
+
+if __name__ == '__main__':
+    main()
--- a/examples/example-pt-infer.py
+++ b/examples/example-pt-infer.py
@@ -0,0 +1,22 @@
+
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+def main():
+    model_name="Norod78/distilgpt2-base-pretrained-he"
+
+    prompt_text = "שלום, קוראים לי"
+    generated_max_length = 192
+
+    print("Loading model...")
+    model =  AutoModelForCausalLM.from_pretrained(model_name)
+    print('Loading Tokenizer...')
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    text_generator = pipeline(task="text-generation", model=model, tokenizer=tokenizer)
+
+    print("Generating text...")
+    result = text_generator(prompt_text, num_return_sequences=1, batch_size=1, do_sample=True, top_k=40, top_p=0.92, temperature = 1, repetition_penalty=5.0, max_length = generated_max_length)
+
+    print("result = " + str(result))
+
+if __name__ == '__main__':
+    main()
--- a/flax_model.msgpack
+++ b/flax_model.msgpack
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd66d0947597bba20a2b75f319583ca7b53d076ec936a773d6b3a36988a83dc1
+size 327652826
--- a/merges.txt
+++ b/merges.txt
--- a/model.onnx
+++ b/model.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19488d4816b80dfa4b019866f792ea80479aa256a131d08c34837f8d8798a87a
+size 488438673
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d267cc8715f3cc03792125f1a204e742a66e15bc7d6d704718c42a685e09819c
+size 333950622
--- a/pytorch_model.bin
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e2f5f0981ee6cd04ad96f75d4efa3e3d60805c1ef7582a9c36310c84bfe783
+size 333969117
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/tf_model.h5
+++ b/tf_model.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4014e881a4e0697013cc2743b861b7fb326d0788326e7804c5a0bcfbb563c7b
+size 327744824
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "./distilgpt2-base-pretrained-he",
+  "special_tokens_map_file": "./distilgpt2-base-pretrained-he/special_tokens_map.json",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e125ee34b8024c8d459873f8d086614ae564cf87b4eb1946507fe379c695479
+size 3439
--- a/vocab.json
+++ b/vocab.json
				`@@ -0,0 +1 @@`
				`model.mlmodel filter=lfs diff=lfs merge=lfs -text`