Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* 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
+llama3-eng-ko-8-llama-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama3-eng-ko-8-llama-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+language:
+- en
+- ko
+pipeline_tag: translation
+tags:
+- llama-3-ko
+- TensorBlock
+- GGUF
+license: mit
+datasets:
+- 4yo1/llama3_enkor_testing_short
+base_model: 4yo1/llama3-eng-ko-8-llama
+---
+
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;">
+            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
+        </p>
+    </div>
+</div>
+
+## 4yo1/llama3-eng-ko-8-llama - GGUF
+
+This repo contains GGUF format model files for [4yo1/llama3-eng-ko-8-llama](https://huggingface.co/4yo1/llama3-eng-ko-8-llama).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+## Prompt template
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [llama3-eng-ko-8-llama-Q2_K.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [llama3-eng-ko-8-llama-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [llama3-eng-ko-8-llama-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [llama3-eng-ko-8-llama-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [llama3-eng-ko-8-llama-Q4_0.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [llama3-eng-ko-8-llama-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [llama3-eng-ko-8-llama-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [llama3-eng-ko-8-llama-Q5_0.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [llama3-eng-ko-8-llama-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [llama3-eng-ko-8-llama-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [llama3-eng-ko-8-llama-Q6_K.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [llama3-eng-ko-8-llama-Q8_0.gguf](https://huggingface.co/tensorblock/llama3-eng-ko-8-llama-GGUF/tree/main/llama3-eng-ko-8-llama-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
+
+
+## Downloading instruction
+
+### Command line
+
+Firstly, install Huggingface Client
+
+```shell
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, downoad the individual model file the a local directory
+
+```shell
+huggingface-cli download tensorblock/llama3-eng-ko-8-llama-GGUF --include "llama3-eng-ko-8-llama-Q2_K.gguf" --local-dir MY_LOCAL_DIR
+```
+
+If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
+
+```shell
+huggingface-cli download tensorblock/llama3-eng-ko-8-llama-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

llama3-eng-ko-8-llama-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88e7b5b1fc97b754443efa87662d7fdecc1b5301a41b66097eaceebc9801671
+size 3179131712

llama3-eng-ko-8-llama-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:514bd171e473fa491cf372888ab998efd9fc28e5623c8a411340eb291a2ba09a
+size 4321956672

llama3-eng-ko-8-llama-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cca3538bb467cda997a0b5a58f130054c46d90cf06dccba0d6ba685cdff13bd
+size 4018918208

llama3-eng-ko-8-llama-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7af8383e0917ac13e902fdeafe8b5ba00155268ba96c15e15102d8e6aaffb9
+size 3664499520

llama3-eng-ko-8-llama-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c27aa3230b46d4b63f9865c2a4f4122fc84c53268b7111473cd3763a44a7c8
+size 4661211968

llama3-eng-ko-8-llama-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e80c7ad32487268908589370143eedad32af0b07874a0c7e50ac9db2dc8066
+size 4920734528

llama3-eng-ko-8-llama-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a096f7e5ad0fc2bca7199902225940c18ad2698359b786574132da4e6ae13d2
+size 4692669248

llama3-eng-ko-8-llama-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e31cc4aa706bbb5fe878177d8a41ef89ca135d86e1b6e8746ac4c0a0fb1e5a1
+size 5599294272

llama3-eng-ko-8-llama-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3f212388ae60b1d636dcb569d822fc21f2c19466e3a81cd054f1732550bd04
+size 5732987712

llama3-eng-ko-8-llama-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6730998dd53b53e10b03d84b4d9917b23d48a4789af5b907e8a1a8a750ae6a8
+size 5599294272

llama3-eng-ko-8-llama-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b04278bd2fc569294524c6221ec460532772dd843ccf3741cf9e8ca944bbca
+size 6596006720

llama3-eng-ko-8-llama-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffec0e8db5b0f0ee0c2122960b488f307d84804e22398632434efb9736b1a193
+size 8540771136