初始化项目，由ModelHub XC社区提供模型

Model: NorGLM/NorGPT-3B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- 'no'
+---
+
+Gnerative Pretrained Tranformer with 3 Billion parameters for Norwegian.
+
+It belongs to NorGLM, a suite of pretrained Norwegian Generative Language Models (NorGLMs). The model is based on GPT2 architecture. NorGLM can be used for non-commercial purposes.
+
+## Datasets
+
+All models in NorGLM are trained on 200G datasets, nearly 25B tokens, including Norwegian, Denish, Swedish, Germany and English.
+
+## Run the Model
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "NorGLM/NorGPT-3B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map='auto',
+    torch_dtype=torch.bfloat16
+)
+
+text = "Tom ønsket å gå på barene med venner"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=20)
+```
+
+## Citation Information
+If you feel our work is helpful, please cite our papers:
+
+```
+@article{gulla2026norwai,
+  title={NorwAI's Large Language Models: Technical Report},
+  author={Gulla, Jon Atle and Liu, Peng and Zhang, Lemei},
+  journal={arXiv preprint arXiv:2601.03034},
+  year={2026}
+}
+
+@inproceedings{liu2024nlebench+,
+  title={NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian},
+  author={Liu, Peng and Zhang, Lemei and Farup, Terje and Lauvrak, Even and Ingvaldsen, Jon and Eide, Simen and Gulla, Jon Atle and Yang, Zhirong},
+  booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
+  pages={5543--5560},
+  year={2024}
+}
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 2688,
+  "n_head": 32,
+  "n_inner": 10752,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "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,
+  "tokenizer_class": "GPT2TokenizerFast",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bfcbd184b430e46c2142366372bfb2ab7586167f00719c27145253d0cf6db6
+size 6174868456

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee33b61ec6603faab950feca42fdf7f7225d45de42cf99cf168f61bcfb6881e9
+size 6174963749

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}