README.md

---
extra_gated_heading: Access Llama-2-Ko on Hugging Face
extra_gated_button_content: Submit
extra_gated_fields:
  I agree to share my name, email address and username: checkbox
  I confirm that I understand this project is for research purposes only, and confirm that I agree to follow the LICENSE of this model: checkbox
language:
- en
- ko
pipeline_tag: text-generation
inference: false
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
- kollama
- llama-2-ko
license: cc-by-nc-sa-4.0
---

> 🚧 Note: this repo is under construction 🚧

# **Llama-2-Ko** 🦙🇰🇷

Llama-2-Ko serves as an advanced iteration of Llama 2, benefiting from an expanded vocabulary and the inclusion of a Korean corpus in its further pretraining. Just like its predecessor, Llama-2-Ko operates within the broad range of generative text models that stretch from 7 billion to 70 billion parameters. This repository focuses on the **70B** pretrained version, which is tailored to fit the Hugging Face Transformers format. For access to the other models, feel free to consult the index provided below.

## Model Details

**Model Developers** Junbum Lee (Beomi)

**Variations** Llama-2-Ko will come in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.

**Input** Models input text only.

**Output** Models generate text only.

## Usage

**Use with 8bit inference**

- Requires > 74GB vram (compatible with 4x RTX 3090/4090 or 1x A100/H100 80G or 2x RTX 6000 ada/A6000 48G)

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_8bit = AutoModelForCausalLM.from_pretrained(
    "beomi/llama-2-ko-70b", 
    load_in_8bit=True,
    device_map="auto",
)
tk = AutoTokenizer.from_pretrained('beomi/llama-2-ko-70b')
pipe = pipeline('text-generation', model=model_8bit, tokenizer=tk)

def gen(x):
    gended = pipe(f"### Title: {x}\n\n### Contents:",  # Since it this model is NOT finetuned with Instruction dataset, it is NOT optimal prompt.
        max_new_tokens=300,
        top_p=0.95,
        do_sample=True,
    )[0]['generated_text']
    print(len(gended))
    print(gended)
```

**Use with bf16 inference**

- Requires > 150GB vram (compatible with 8x RTX 3090/4090 or 2x A100/H100 80G or 4x RTX 6000 ada/A6000 48G)

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model = AutoModelForCausalLM.from_pretrained(
    "beomi/llama-2-ko-70b", 
    device_map="auto",
)
tk = AutoTokenizer.from_pretrained('beomi/llama-2-ko-70b')
pipe = pipeline('text-generation', model=model, tokenizer=tk)

def gen(x):
    gended = pipe(f"### Title: {x}\n\n### Contents:",  # Since it this model is NOT finetuned with Instruction dataset, it is NOT optimal prompt.
        max_new_tokens=300,
        top_p=0.95,
        do_sample=True,
    )[0]['generated_text']
    print(len(gended))
    print(gended)
```

**Model Architecture** 

Llama-2-Ko is an auto-regressive language model that uses an optimized transformer architecture based on Llama-2.

||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama-2-Ko 70B|*A new mix of Korean online data*|70B|4k|✅|>20B|1e<sup>-5</sup>|
*Plan to train upto 300B tokens

**Vocab Expansion**

| Model Name | Vocabulary Size | Description | 
| --- | --- | --- |
| Original Llama-2 | 32000 | Sentencepiece BPE |
| **Expanded Llama-2-Ko** | 46592 | Sentencepiece BPE. Added Korean vocab and merges |
*Note: Llama-2-Ko 70B uses `46592` not `46336`(7B), will update new 7B model soon.

**Tokenizing "안녕하세요, 오늘은 날씨가 좋네요. ㅎㅎ"**

| Model | Tokens |
| --- | --- |
| Llama-2 | `['▁', '안', '<0xEB>', '<0x85>', '<0x95>', '하', '세', '요', ',', '▁', '오', '<0xEB>', '<0x8A>', '<0x98>', '은', '▁', '<0xEB>', '<0x82>', '<0xA0>', '씨', '가', '▁', '<0xEC>', '<0xA2>', '<0x8B>', '<0xEB>', '<0x84>', '<0xA4>', '요', '.', '▁', '<0xE3>', '<0x85>', '<0x8E>', '<0xE3>', '<0x85>', '<0x8E>']` |
| Llama-2-Ko *70B | `['▁안녕', '하세요', ',', '▁오늘은', '▁날', '씨가', '▁좋네요', '.', '▁', 'ㅎ', 'ㅎ']` |

**Tokenizing "Llama 2: Open Foundation and Fine-Tuned Chat Models"**

| Model | Tokens |
| --- | --- |
| Llama-2 | `['▁L', 'l', 'ama', '▁', '2', ':', '▁Open', '▁Foundation', '▁and', '▁Fine', '-', 'T', 'un', 'ed', '▁Ch', 'at', '▁Mod', 'els']` |
| Llama-2-Ko 70B | `['▁L', 'l', 'ama', '▁', '2', ':', '▁Open', '▁Foundation', '▁and', '▁Fine', '-', 'T', 'un', 'ed', '▁Ch', 'at', '▁Mod', 'els']` |

# **Model Benchmark**

## LM Eval Harness - Korean (polyglot branch)

- Used EleutherAI's lm-evaluation-harness https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot

### TBD

## Note for oobabooga/text-generation-webui

Remove `ValueError` at `load_tokenizer` function(line 109 or near), in `modules/models.py`.

```python
diff --git a/modules/models.py b/modules/models.py
index 232d5fa..de5b7a0 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -106,7 +106,7 @@ def load_tokenizer(model_name, model):
                 trust_remote_code=shared.args.trust_remote_code,
                 use_fast=False
             )
-        except ValueError:
+        except:
             tokenizer = AutoTokenizer.from_pretrained(
                 path_to_model,
                 trust_remote_code=shared.args.trust_remote_code,
```

Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, 
it is required to use `use_fast=True` option when initialize tokenizer.

Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU)

## LICENSE

- Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License, under LLAMA 2 COMMUNITY LICENSE AGREEMENT
- Full License available at: [https://huggingface.co/beomi/llama-2-ko-70b/blob/main/LICENSE](https://huggingface.co/beomi/llama-2-ko-70b/blob/main/LICENSE)
- For Commercial Usage, contact Author.

## Citation

```
@misc {l._junbum_2023,
	author       = { {L. Junbum} },
	title        = { llama-2-ko-70b },
	year         = 2023,
	url          = { https://huggingface.co/beomi/llama-2-ko-70b },
	doi          = { 10.57967/hf/1130 },
	publisher    = { Hugging Face }
}
```

## Acknowledgement

The training is supported by [TPU Research Cloud](https://sites.research.google/trc/) program.