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
+koquality-ko-ref-llama2-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+koquality-ko-ref-llama2-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+datasets:
+- DILAB-HYU/KoQuality
+language:
+- ko
+pipeline_tag: text-generation
+tags:
+- KoQuality
+- llama
+- TensorBlock
+- GGUF
+base_model: DILAB-HYU/koquality-ko-ref-llama2-7b
+---
+
+<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>
+
+## DILAB-HYU/koquality-ko-ref-llama2-7b - GGUF
+
+This repo contains GGUF format model files for [DILAB-HYU/koquality-ko-ref-llama2-7b](https://huggingface.co/DILAB-HYU/koquality-ko-ref-llama2-7b).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
+
+## Prompt template
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [koquality-ko-ref-llama2-7b-Q2_K.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
+| [koquality-ko-ref-llama2-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q3_K_S.gguf) | Q3_K_S | 2.948 GB | very small, high quality loss |
+| [koquality-ko-ref-llama2-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q3_K_M.gguf) | Q3_K_M | 3.298 GB | very small, high quality loss |
+| [koquality-ko-ref-llama2-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q3_K_L.gguf) | Q3_K_L | 3.597 GB | small, substantial quality loss |
+| [koquality-ko-ref-llama2-7b-Q4_0.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q4_0.gguf) | Q4_0 | 3.826 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [koquality-ko-ref-llama2-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q4_K_S.gguf) | Q4_K_S | 3.857 GB | small, greater quality loss |
+| [koquality-ko-ref-llama2-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q4_K_M.gguf) | Q4_K_M | 4.081 GB | medium, balanced quality - recommended |
+| [koquality-ko-ref-llama2-7b-Q5_0.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q5_0.gguf) | Q5_0 | 4.652 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [koquality-ko-ref-llama2-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q5_K_S.gguf) | Q5_K_S | 4.652 GB | large, low quality loss - recommended |
+| [koquality-ko-ref-llama2-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q5_K_M.gguf) | Q5_K_M | 4.783 GB | large, very low quality loss - recommended |
+| [koquality-ko-ref-llama2-7b-Q6_K.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q6_K.gguf) | Q6_K | 5.529 GB | very large, extremely low quality loss |
+| [koquality-ko-ref-llama2-7b-Q8_0.gguf](https://huggingface.co/tensorblock/koquality-ko-ref-llama2-7b-GGUF/blob/main/koquality-ko-ref-llama2-7b-Q8_0.gguf) | Q8_0 | 7.161 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/koquality-ko-ref-llama2-7b-GGUF --include "koquality-ko-ref-llama2-7b-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/koquality-ko-ref-llama2-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

koquality-ko-ref-llama2-7b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c27e4f912d7f06e681e2eaad9720ecffe7fd3526171185dda72c5d753bc6d59
+size 2532864640

koquality-ko-ref-llama2-7b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181c4774e4fdfde32ef2ad3d0ba08c27da83efa937cefa6a70b100a9c0e96f0d
+size 3597111936

koquality-ko-ref-llama2-7b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad33ae06ceb706dd5aa39cc037ecfd2fac7e29a23cc5f1c7bc0e5a7ce2c2e7dd
+size 3298005632

koquality-ko-ref-llama2-7b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef72b76d73d11886219333966a515324bc5c833d043004052ce8772e9ad9bb6e
+size 2948305536

koquality-ko-ref-llama2-7b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f6a84e73930985d4fc519da697d7954ddbd68c5be7ffa5cfbda24689b83709
+size 3825808000

koquality-ko-ref-llama2-7b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca340db219b4ac6a192b911a98d4e6cb25c7c7eebc4f0e806aa458605e5f4001
+size 4081005184

koquality-ko-ref-llama2-7b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d6925346ecf105414ed6abfa0c7a5930f1711b65cc548c67e2aa32637afb17
+size 3856740992

koquality-ko-ref-llama2-7b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94d267c19f9be54466fccb35436734e9abb05fef31f048ab55e9d3021b5b994
+size 4651692672

koquality-ko-ref-llama2-7b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a039d7f17f014e3540710b9913483a0b17f74a67be95d932486aeaed32b2bc4
+size 4783157888

koquality-ko-ref-llama2-7b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6699147694cffbab9d732ec9f375e8a6ef070679f1188c7e4af635c3bfffb85d
+size 4651692672

koquality-ko-ref-llama2-7b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7c856381f214f8d52aee47a143973b0e60a9af102b9701553ab7bd1edb1433
+size 5529195136

koquality-ko-ref-llama2-7b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120f7f07f2af3977b059755f091cfedb22b2f14f0fde16b792fa20706a6549e7
+size 7161090688