---
base_model:
- Bllossom/llama-3-Korean-Bllossom-70B
library_name: transformers
tags:
- mergekit
- merge

---
🌋🌋 Huggingface Upload Issue

Maximum individual file size is 50.0GB to upload huggingface.

To clear it, Split the file into part_aa, part_ab, part_ac chunks as my "Practical Idea".

After you download this repo on your folder path, command like this.

```
cat part_* > llama-3-korean-bllossom-120b-Q4_K_M.gguf
```

I thought uploading it as a GGUF rather than a simple original file was for your benefit, so I'm uploading it like this even if it takes a bit of trouble.
```
Perhaps this will be the first GGUF model to upload such a large GGUF file of over 50GB to huggingface?

Sometimes we need to use a trick called chunks.

```

Please wait to upload..... 

### 🇰🇷 About the JayLee "AsianSoul"

```
"A leader who can make you rich 💵 !!!"

"Prove yourself with actual results, not just saying I know more than you!!!"
```

<a href="https://ibb.co/4g2SJVM"><img src="https://i.ibb.co/PzMWt64/Screenshot-2024-05-18-at-11-08-12-PM.png" alt="Screenshot-2024-05-18-at-11-08-12-PM" border="0"></a>

### About this model

This is a 128B model based on [Bllossom/llama-3-Korean-Bllossom-70B](https://huggingface.co./Bllossom/llama-3-Korean-Bllossom-70B)

☕ I started this Korean 120B model merge while drinking an iced Americano at Starbucks referring to other [Cognitive Computations 120B](https://huggingface.co./cognitivecomputations/MegaDolphin-120b).

If you walk around Starbucks in Seoul, Korea, you will see someone creating a merge and an application based on it. 

At that time, please come up to me and say "hello".

🏎️ I am a person whose goal is to turn the great results created by great genius scientists & groups around the world into profitable ones.

```
My role model is J. Robert Oppenheimer!!!

J. Robert Oppenheimer is highly regarded for his ability to gather and lead a team of brilliant scientists, merging their diverse expertise and efforts towards a common goal. 
```
[Learn more about J. Robert Oppenheimer](https://en.wikipedia.org/wiki/J._Robert_Oppenheimer).

I hope this 120B is a helpful model for your future.

```
🌍 Collaboration is always welcome 🌍

👊 You can't beat these giant corporations & groups alone and you can never become rich. 

Now we have to come together. 

People who can actually become rich together, let's collaborate with me.!!! 🍸
```

```
About Bllossom/llama-3-Korean-Bllossom-70B
- Full model released in Korean over 100GB by Blossom team
- First in Korean! Expansion of Korean vocabulary to over 30,000 words
- Capable of processing Korean context that is approximately 25% longer than Llama3
- Connecting Korean-English knowledge using the Korean-English Parallel Corpus (pre-study)
- Fine tuning using data produced by linguists considering Korean culture and language
- Reinforcement learning

🛰️ About asiansoul/llama-3-Korean-Bllossom-120B-GGUF
- Q4_K_M : On a GPU with 68GB / more OR a CPU with 68G / more memory
- More Quantization ones i hope to upload, but your computer won't be able to handle it then. you know what i mean!!
```

### Models Merged

The following models were included in the merge:
* [Bllossom/llama-3-Korean-Bllossom-70B](https://huggingface.co./Bllossom/llama-3-Korean-Bllossom-70B)


### Ollama 

Check the information indicated above and run it when your computer is ready. 

Otherwise, your computer will freeze.

* Create

```
ollama create Bllossom -f ./Modelfile_Q4_K_M 

```

* MODELFILE (you can change this for your preference)

```
FROM llama-3-korean-bllossom-120b-Q4_K_M.gguf
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""


SYSTEM """
친절한 챗봇으로서 상대방의 요청에 최대한 자세하고 친절하게 답하자. 모든 대답은 한국어(Korean)으로 대답해줘.
"""

PARAMETER num_keep 24
PARAMETER temperature 0.7
PARAMETER num_predict 3000
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
```

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
- sources:
  - layer_range: [0, 20]
    model: Bllossom/llama-3-Korean-Bllossom-70B
- sources:
  - layer_range: [10, 30]
    model: Bllossom/llama-3-Korean-Bllossom-70B
- sources:
  - layer_range: [20, 40]
    model: Bllossom/llama-3-Korean-Bllossom-70B
- sources:
  - layer_range: [30, 50]
    model: Bllossom/llama-3-Korean-Bllossom-70B
- sources:
  - layer_range: [40, 60]
    model: Bllossom/llama-3-Korean-Bllossom-70B
- sources:
  - layer_range: [50, 70]
    model: Bllossom/llama-3-Korean-Bllossom-70B
- sources:
  - layer_range: [60, 80]
    model: Bllossom/llama-3-Korean-Bllossom-70B
merge_method: passthrough
dtype: float16

```