初始化项目，由ModelHub XC社区提供模型

Model: UUFO-Aigis/PicoLAiNN-100M-SmallDataset
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

Inferencecode.py

@@ -0,0 +1,35 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+MODEL_NAME = "UUFO-Aigis/Pico-OpenLAiNN-100M" #Replace 100M with 250M or 500M 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 +1,79 @@
+# Pico-OpenLAiNN-testing 🤗
+
+Hey there fellow researchers, developers, and AI enthusiasts! Today I'm releasing a *smol* open LLM. This is mainly just a test and I plan to release actually usable models in the near future.
+## Models Overview
+
+- **Pico-OpenLAiNN-100M-SmallData**: The smallest of the bunch, this 100M parameter model is perfect for quick experiments and applications where computational resources are *extremely* limited.
+
+## Pretraining Details
+
+This specific version of Pico LAiNN was trained on just 8 billion tokens of the fineweb dataset.
+
+## 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/Pico-OpenLAiNN-100M" #Replace 100M with 250M or 500M 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()
+```
+## Benchy :3 
+|    Tasks     | Value |   |Stderr|
+|--------------|------:|---|-----:|
+|arc_challenge | 0.1826|±  |0.0113|
+|arc_easy      | 0.3859|±  |0.0100|
+|boolq         | 0.5804|±  |0.0086|
+|hellaswag     | 0.2791|±  |0.0045|
+|lambada_openai| 0.2437|±  |0.0060|
+|piqa          | 0.6159|±  |0.0113|
+|winogrande    | 0.5067|±  |0.0141|
+
+
+
+## Future Plans
+
+- **More Models**: I'm currenetly training the bigger siblings of this models, including a 1B parameter version and beyond. 2-4 Billion parameter versions are planned.
+- **New architecture**: This is still up in the air and I'm still developing it, and will release if I deem it to be actually useful, so stay tuned!
+- **Paper**: A detailed paper 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 🤗

config.json

@@ -0,0 +1,24 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "max_position_embeddings": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 9,
+    "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 sha256:3d547d7cba8a5778865dccba053dadabfb42811bed2addaf3228d2d00a060f7e
+size 207164992

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_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
+}