---
base_model: ahxt/llama2_xs_460M_experimental
datasets:
- Redpajama
inference: false
language:
- en
metrics:
- MMLU
model_creator: ahxt
model_name: llama2_xs_460M_experimental
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- llama2
- llama-2
- llama
- llama2 architecture
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
---
# ahxt/llama2_xs_460M_experimental-GGUF

Quantized GGUF model files for [llama2_xs_460M_experimental](https://huggingface.co/ahxt/llama2_xs_460M_experimental) from [ahxt](https://huggingface.co/ahxt)


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [llama2_xs_460m_experimental.q2_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental-GGUF/resolve/main/llama2_xs_460m_experimental.q2_k.gguf) | q2_k | 212.56 MB  |
| [llama2_xs_460m_experimental.q3_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental-GGUF/resolve/main/llama2_xs_460m_experimental.q3_k_m.gguf) | q3_k_m | 238.87 MB  |
| [llama2_xs_460m_experimental.q4_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental-GGUF/resolve/main/llama2_xs_460m_experimental.q4_k_m.gguf) | q4_k_m | 288.51 MB  |
| [llama2_xs_460m_experimental.q5_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental-GGUF/resolve/main/llama2_xs_460m_experimental.q5_k_m.gguf) | q5_k_m | 333.29 MB  |
| [llama2_xs_460m_experimental.q6_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental-GGUF/resolve/main/llama2_xs_460m_experimental.q6_k.gguf) | q6_k | 380.87 MB  |
| [llama2_xs_460m_experimental.q8_0.gguf](https://huggingface.co/afrideva/llama2_xs_460M_experimental-GGUF/resolve/main/llama2_xs_460m_experimental.q8_0.gguf) | q8_0 | 492.67 MB  |



## Original Model Card:
# LLaMa Lite: Reduced-Scale, Experimental Versions of LLaMA and LLaMa 2

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.


### 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/llama2_xs_460M_experimental'
model_path = 'ahxt/llama1_s_1.8B_experimental'

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
markdown table
| 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 |
| llama2_xs_460M              | 0.46B | 21.13 | 26.39 |




## Contact
This experimental version is developed by:
[Xiaotian Han](https://ahxt.github.io/) from Texas A&M University. And these experimental verisons are for research only.











# [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         |