Added Model files.

Inferencecode.py

@@ -0,0 +1,35 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+MODEL_NAME = "UUFO-Aigis/Pico-OpenLAiNN-25M" #Replace 25M with 10M, 50M or 75M if you prefer those models.
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+
+def generate_text(prompt, model, tokenizer, max_length=512, temperature=1, top_k=50, top_p=0.95):
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+
+    outputs = model.generate(
+        inputs,
+        max_length=max_length,
+        temperature=temperature,
+        top_k=top_k,
+        top_p=top_p,
+        do_sample=True
+    )
+
+
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+
+def main():
+    # Define your prompt
+    prompt = "According to all known laws of aviation, there is no way a bee should be able to fly."
+
+    generated_text = generate_text(prompt, model, tokenizer)
+
+    print(generated_text)
+
+if __name__ == "__main__":
+    main()

README.md

@@ -0,0 +1,85 @@
+# Planck-OpenLAiNN 🤗
+
+Hey there fellow researchers, developers, and AI enthusiasts! Today I'm releasing a new family of Models, Planck LAiNN, These are probably some of the smallest LLMs that are on HF. They aren't super useful but it was a fun expierment!~
+## Models Overview
+- **Panck-OpenLAiNN-10M**: A Truely Tiny model with just 10 Million parameters, this is probably boarderline useless, but it *IS* functional.
+- **Panck-OpenLAiNN-25M**: The second smallest model, 25 million parameters, it's not that much better.
+- **Panck-OpenLAiNN-50M**: Surprisingly smart, it's 50 Million parameters and could potentially maybe, Possibly even be useful ;)
+- **Panck-OpenLAiNN-75M**: The current *""heavy""* weight of the Plank-OpenLAiNN Models.
+## Pretraining Details
+
+Plank-OpenLAiNN was trained on 32B tokens of the Fineweb dataset, it's the same one that was used for the Pico-LAiNN family of models. The model was pretrained with a context length of 1024 tokens.
+
+## Other information:
+
+- **Compatibility**: Built to be compatible with existing projects that use LLAMA 2's tokenizer and architecture.
+- **Ease of Use**: No need to reinvent the wheel. These models are ready to be plugged into your applications.
+- **Open Source**: Fully open source, so you can tweak, tune, and twist them to your heart's content.
+## Getting Started
+
+To start using these models, you can simply load them via the Hugging Face `transformers` library:
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+MODEL_NAME = "UUFO-Aigis/Panck-OpenLAiNN-25M"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+
+def generate_text(prompt, model, tokenizer, max_length=512, temperature=1, top_k=50, top_p=0.95):
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+
+    outputs = model.generate(
+        inputs,
+        max_length=max_length,
+        temperature=temperature,
+        top_k=top_k,
+        top_p=top_p,
+        do_sample=True
+    )
+
+
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+
+def main():
+    # Define your prompt
+    prompt = "According to all known laws of aviation, there is no way a bee should be able to fly."
+
+    generated_text = generate_text(prompt, model, tokenizer)
+
+    print(generated_text)
+
+if __name__ == "__main__":
+    main()
+```
+# Benchy
+
+|    Tasks     | Value |   |Stderr|
+|--------------|------:|---|-----:|
+|arc_challenge | 0.1817|±  |0.0113|
+|arc_easy      | 0.3291|±  |0.0096|
+|boolq         | 0.6138|±  |0.0085|
+|hellaswag     | 0.2700|±  |0.0044|
+|lambada_openai| 0.1104|±  |0.0044|
+|piqa          | 0.5740|±  |0.0115|
+|winogrande    | 0.5170|±  |0.0140|
+
+## Future Plans
+
+- **More Models**: I'm currenetly training the bigger siblings of Pico-OpenLAiNN, including a 1B parameter version and beyond. 2-4 Billion parameter versions are planned. These will be Released as OpenLAiNN.
+- **New architecture**: This is still up in the air and I'm still developing it, things are going well and I'll post updates.
+- **Paper**: A detailed paper or training data will be posted at some point. 
+
+## Credit Where Credit's Due
+
+If you find these models useful and decide to use these models, a link to this repository would be highly appreciated. I am a one man show running this, Thanks 🤗
+## Contact
+If you have questions, Please reach out to me at urlsys32dll@gmail.com
+
+<p align="center">
+  <img src="UUFO.png" alt="U.U.F.O Research Logo" width="250"/>
+</p>

config.json

@@ -0,0 +1,24 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "max_position_embeddings": 1024,
+    "model_type": "llama",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.31.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e18dadf15428f990e4a112b9f725d2bc0cea67e10b98e63d7d4ef1a6600721
+size 55351256

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}