Upload folder using huggingface_hub

README.md

@@ -0,0 +1,51 @@
+# ak-lm-small
+
+**Tiny pretrained Malayalam language model (75M parameters)**
+
+Developed by **EnduraSolution**.
+
+## Overview
+
+- GPT-style decoder-only Transformer
+- 75 Million parameters
+- Custom Malayalam SentencePiece tokenizer
+- Vocabulary: 24,000
+- Context length: 256
+
+## Training Data
+
+- IndicCorp Malayalam
+- Malayalam Wikipedia
+- Kerala-focused corpus
+- Small English Wikipedia subset
+
+## Intended Uses
+
+- Malayalam text generation
+- Text completion
+- Research
+- Fine-tuning
+
+## Limitations
+
+This is a pretrained base model.
+
+It is **not instruction tuned**.
+
+## Example
+
+```python
+from transformers import GPT2LMHeadModel
+import sentencepiece as spm
+
+sp = spm.SentencePieceProcessor(model_file='ml_sp.model')
+model = GPT2LMHeadModel.from_pretrained('endurasolution/ak-lm-small')
+```
+
+## License
+
+Apache-2.0
+
+---
+
+Made with ❤️ by EnduraSolution

config.json

@@ -0,0 +1,35 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 256,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 8,
+  "n_positions": 256,
+  "pad_token_id": 3,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 24000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.12.1",
+  "use_cache": true
+}

ml_sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f460a367d49d8d35091821f3b92db32bdf7fb14d6f6b2b749f04b495d159f5
+size 711965

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bed2a4bcc21846d6afd8a1071e76e1b88e0fab8c8a2642ecc68a039e86473f
+size 301342544

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef38437d55269a1754b136a4079f51e8a6449426af0232554c4ddd06d09038aa
+size 5201