Duplicate from anrilombard/mzansilm-125m

Co-authored-by: Anri Lombard <anrilombard@users.noreply.huggingface.co>

.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 +1,111 @@
+---
+language:
+- af
+- en
+- nso
+- sot
+- ssw
+- tsn
+- tso
+- ven
+- xho
+- zul
+- nbl
+tags:
+- llama
+- south-african-languages
+- low-resource
+- decoder-only
+- mzansilm
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# MzansiLM 125M
+
+**MzansiLM** is a 125M-parameter decoder-only language model trained from scratch on **MzansiText**, a multilingual corpus covering all eleven official South African languages.
+
+[![GitHub](https://img.shields.io/badge/GitHub-Anri--Lombard/sallm-blue)](https://github.com/Anri-Lombard/sallm)
+[![Paper](https://img.shields.io/badge/Paper-arXiv_2603.20732-red.svg)](https://arxiv.org/abs/2603.20732)
+[![Dataset](https://img.shields.io/badge/Dataset-MzansiText-green)](https://huggingface.co/datasets/anrilombard/mzansi-text)
+[![Collection](https://img.shields.io/badge/Collection-MzansiLM-orange)](https://huggingface.co/collections/anrilombard/mzansilm-69635ca7b60efedb9dfcb09e)
+
+## Model Details
+
+- Parameters: `125,008,384`
+- Architecture: decoder-only `LlamaForCausalLM`
+- Hidden size: `512`
+- Intermediate size: `1536`
+- Layers: `30`
+- Attention heads: `9`
+- Key/value heads: `3`
+- Context length: `2048`
+- RoPE theta: `10000.0`
+- RMSNorm epsilon: `1e-5`
+- Tied word embeddings: `true`
+- Training attention implementation: `flash_attention_2`
+
+## Tokenizer
+
+MzansiLM uses a custom BPE tokenizer with a vocabulary size of `65536`.
+
+- `[BOS] = 0`
+- `[EOS] = 1`
+- `[PAD] = 2`
+- `[UNK] = 3`
+- Normalizer: `NFD`
+- Pre-tokenizer: `ByteLevel`
+- Post-processing:
+  - single sequence: `[BOS] $A [EOS]`
+  - pair sequence: `[BOS] $A [EOS] [BOS] $B [EOS]`
+
+## Training Data
+
+The model was trained on **MzansiText** and covers all eleven official South African languages:
+
+`af`, `en`, `nso`, `sot`, `ssw`, `tsn`, `tso`, `ven`, `xho`, `zul`, `nbl`
+
+Related releases:
+
+- Paper: [arXiv:2603.20732](https://arxiv.org/abs/2603.20732)
+- Raw corpus: [anrilombard/mzansi-text](https://huggingface.co/datasets/anrilombard/mzansi-text)
+- Tokenized corpus: [anrilombard/mzansi-text-tokenized](https://huggingface.co/datasets/anrilombard/mzansi-text-tokenized)
+- GitHub code and configs: [https://github.com/Anri-Lombard/sallm](https://github.com/Anri-Lombard/sallm)
+
+## Intended Use
+
+MzansiLM is a research model for pretraining, fine-tuning, and evaluation on South African languages. It is intended as a reproducible baseline for language modeling and downstream task adaptation.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("anrilombard/mzansilm-125m")
+model = AutoModelForCausalLM.from_pretrained("anrilombard/mzansilm-125m")
+
+inputs = tokenizer("Molo!", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Citation
+
+Please cite the paper:
+
+```bibtex
+@misc{lombard2026mzansitextmzansilmopencorpus,
+      title={MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages}, 
+      author={Anri Lombard and Simbarashe Mawere and Temi Aina and Ethan Wolff and Sbonelo Gumede and Elan Novick and Francois Meyer and Jan Buys},
+      year={2026},
+      eprint={2603.20732},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2603.20732}, 
+}
+```
+
+## License
+
+Apache License 2.0

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "head_dim": 56,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 65536,
+  "pad_token_id": 2
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "transformers_version": "4.52.4",
+  "pad_token_id": 2
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89dd7bef29566a9623c382da5d1416e38c605b1c3284ab6a22c9591fb94d593
+size 500063944

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7388b67c8fe73a1bb8f80a97b8b756de4a110e914ac8e1dfcaf0d06697a61273
+size 500125578

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ]
+}