first commit

.gitattributes copy

@@ -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

@@ -1,3 +1,93 @@
 ---
+language: 
+  - en
+tags:
+- llama2
+- llama-2
+- llama
+- llama2 architecture
+- litellama
+datasets:
+- Redpajama
+metrics:
+- MMLU
 license: mit
 ---
+
+# LiteLLama: Reduced-Scale, Experimental Versions of Llama
+
+In this series of repos, we present an open-source reproduction of Meta AI's [LLaMA](https://ai.meta.com/blog/large-language-model-llama-meta-ai/) and [LLaMa 2](https://ai.meta.com/llama/) large language models. However, with significantly reduced model sizes, the experimental version of [llama1_s](https://huggingface.co/ahxt/llama1_s_1.8B_experimental) has 1.8B parameters, and the experimental version of [llama2_xs](https://huggingface.co/ahxt/llama2_xs_460M_experimental) has 460M parameters. ('s' stands for small, while 'xs' denotes extra small).
+
+
+## Dataset and Tokenization
+We train our models on part of [RedPajama](https://www.together.xyz/blog/redpajama) dataset. We use the [GPT2Tokenizer](https://huggingface.co/docs/transformers/v4.31.0/en/model_doc/gpt2#transformers.GPT2Tokenizer) to tokenize the text.
+
+## Training Details
+
+The model was trained with ~1T tokens (0.98T). num of tokens = steps*length*batch_size=499679*1024*192=98240888832≈0.98T.
+
+The training curve is at https://wandb.ai/ahxt/llama2_xs_460M_training_loss/reports/reduced_train_loss-23-09-05-20-25-43---Vmlldzo1MzIwNDUx?accessToken=x2ch3n30jo77p1x8y7q9js4h4d8zpjtz1tzot4xxullyefixp4jwt7au2q37k2q6
+
+### Using with HuggingFace Transformers
+The experimental checkpoints can be directly loaded by [Transformers](https://huggingface.co/transformers/) library. The following code snippet shows how to load the our experimental model and generate text with it. 
+
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_path = 'ahxt/LiteLlama-460M-1T'
+
+model = AutoModelForCausalLM.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model.eval()
+
+prompt = 'Q: What is the largest bird?\nA:'
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+tokens = model.generate(input_ids, max_length=20)
+print( tokenizer.decode(tokens[0].tolist(), skip_special_tokens=True) )
+# Q: What is the largest bird?\nA: The largest bird is the bald eagle.
+```
+
+## Evaluation
+
+# We evaluate our models on the MMLU task.
+
+| Models | #parameters |zero-shot |  5-shot |
+| --- | --- | --- | --- |
+| llama                       | 7B    | 28.46 | 35.05 |
+| openllama                   | 3B    | 24.90 | 26.71 |
+|TinyLlama-1.1B-step-50K-105b | 1.1B  | 19.00 | 26.53 |
+| LiteLlama-460M-1T           | 0.46B | 21.13 | 26.39 |
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ahxt__llama2_xs_460M_experimental)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 26.65   |
+| ARC (25-shot)         | 24.91          |
+| HellaSwag (10-shot)   | 38.47    |
+| MMLU (5-shot)         | 26.17         |
+| TruthfulQA (0-shot)   | 41.59   |
+| Winogrande (5-shot)   | 49.88   |
+| GSM8K (5-shot)        | 0.0        |
+| DROP (3-shot)         | 5.51         |
+
+
+
+
+## Contact
+This experimental version is developed by:
+[Xiaotian Han](https://ahxt.github.io/) from Texas A&M University. The model is released 
+
+
+
+
+
+
+
+
+
+

config copy.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e3a81023fd29302653e5d337bb49c806a6ed7e82dea41b83947cf0944cc543
+size 923454681

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "eos_token": "#",
+  "pad_token": "\"",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}