Upload folder using huggingface_hub

README.md

@@ -0,0 +1,38 @@
+---
+language: en
+tags:
+- text-generation
+- plain-english
+- fine-tuned
+datasets:
+- tatsu-lab/alpaca
+---
+
+# PlainEnglish-1B
+
+A 1B parameter text generation model fine-tuned for clear, plain English output.
+
+## Model Details
+
+- **Architecture**: LlamaForCausalLM (TinyLlama-1.1B)
+- **Total Parameters**: 1,100,048,384 (1.1B)
+- **Base Model**: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+- **Training Dataset**: tatsu-lab/alpaca (52K instruction examples)
+- **Fine-tuning Method**: LoRA (rank=64, alpha=128) merged into base
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("PlainEnglish/PlainEnglish-1B")
+tokenizer = AutoTokenizer.from_pretrained("PlainEnglish/PlainEnglish-1B")
+
+inputs = tokenizer("The meaning of life is", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.7, do_sample=True)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "5.10.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1077bd4169c6bc5750d5fe5a39e2e3ef35e1269c4cc99062059a7ac76972c343
+size 4400216536

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_report.json

@@ -0,0 +1,8 @@
+{
+  "model_name": "PlainEnglish-1B",
+  "base_model": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "total_parameters": 1100048384,
+  "training_method": "LoRA (r=64, alpha=128) merged into base",
+  "dataset": "tatsu-lab/alpaca",
+  "training_steps": 10
+}