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
+ko-gemma-2b-it-sft-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+ko-gemma-2b-it-sft-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+language:
+- ko
+- en
+library_name: transformers
+datasets:
+- nlpai-lab/kullm-v2
+tags:
+- TensorBlock
+- GGUF
+base_model: CarrotAI/ko-gemma-2b-it-sft
+---
+
+<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>
+
+## CarrotAI/ko-gemma-2b-it-sft - GGUF
+
+This repo contains GGUF format model files for [CarrotAI/ko-gemma-2b-it-sft](https://huggingface.co/CarrotAI/ko-gemma-2b-it-sft).
+
+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
+
+```
+<bos><start_of_turn>user
+{prompt}<end_of_turn>
+<start_of_turn>model
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [ko-gemma-2b-it-sft-Q2_K.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q2_K.gguf) | Q2_K | 1.158 GB | smallest, significant quality loss - not recommended for most purposes |
+| [ko-gemma-2b-it-sft-Q3_K_S.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q3_K_S.gguf) | Q3_K_S | 1.288 GB | very small, high quality loss |
+| [ko-gemma-2b-it-sft-Q3_K_M.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q3_K_M.gguf) | Q3_K_M | 1.384 GB | very small, high quality loss |
+| [ko-gemma-2b-it-sft-Q3_K_L.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q3_K_L.gguf) | Q3_K_L | 1.466 GB | small, substantial quality loss |
+| [ko-gemma-2b-it-sft-Q4_0.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q4_0.gguf) | Q4_0 | 1.551 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [ko-gemma-2b-it-sft-Q4_K_S.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q4_K_S.gguf) | Q4_K_S | 1.560 GB | small, greater quality loss |
+| [ko-gemma-2b-it-sft-Q4_K_M.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q4_K_M.gguf) | Q4_K_M | 1.630 GB | medium, balanced quality - recommended |
+| [ko-gemma-2b-it-sft-Q5_0.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q5_0.gguf) | Q5_0 | 1.799 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [ko-gemma-2b-it-sft-Q5_K_S.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q5_K_S.gguf) | Q5_K_S | 1.799 GB | large, low quality loss - recommended |
+| [ko-gemma-2b-it-sft-Q5_K_M.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q5_K_M.gguf) | Q5_K_M | 1.840 GB | large, very low quality loss - recommended |
+| [ko-gemma-2b-it-sft-Q6_K.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q6_K.gguf) | Q6_K | 2.062 GB | very large, extremely low quality loss |
+| [ko-gemma-2b-it-sft-Q8_0.gguf](https://huggingface.co/tensorblock/ko-gemma-2b-it-sft-GGUF/blob/main/ko-gemma-2b-it-sft-Q8_0.gguf) | Q8_0 | 2.669 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/ko-gemma-2b-it-sft-GGUF --include "ko-gemma-2b-it-sft-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/ko-gemma-2b-it-sft-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

ko-gemma-2b-it-sft-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9331af494a65c0bad473f0e6fc7064dab4faaf7cf44d81bb7fd817ffee01dcd
+size 1157925248

ko-gemma-2b-it-sft-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a46850d7d6f5edfe1497e05755dab5ce49fada3aa64b8fe4eda1231988d052
+size 1465592192

ko-gemma-2b-it-sft-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6676152894d5d46f101ce66938cd7806f9e406c2730728a9127a60b9b1d8d8aa
+size 1383803264

ko-gemma-2b-it-sft-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22eead42412f0c3d8a9c05fb4e500435f9ded383db2d6cef32981591b84a4f2d
+size 1287981440

ko-gemma-2b-it-sft-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4655825d6c3217279c249cd1eda1b6f99847c0bddf215c39a4197f9aeb969d38
+size 1551190400

ko-gemma-2b-it-sft-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b46ddab608968fae59a1d2e8a0b7ed1be5d664b3f33932da231020a53549327
+size 1630263680

ko-gemma-2b-it-sft-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37bcd09d35182de2ae57396dae9c41ed3639e2c911f2febb3070dd1a69f978cc
+size 1559841152

ko-gemma-2b-it-sft-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5afe93b6ef8e79af08eb093665eb4b3f083c10aa31ec72690858819947c7fd3
+size 1798916480

ko-gemma-2b-it-sft-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a94a83c8a38001d7987a87acd16929d885807e1028eee73e2f89034afdf865b
+size 1839651200

ko-gemma-2b-it-sft-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2668e1d7beb1870443e7a0cc8d498b340bba02ec956bcaa77c2b3f004ff8e2
+size 1798916480

ko-gemma-2b-it-sft-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8130a3357602ad952a27d5c655a05094e24e01de237cfae9bdbf47970a8cd033
+size 2062125440

ko-gemma-2b-it-sft-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26828af1281b75ebec2ca4d7c2255814792dcd397c7a674712df5a80d0d16c74
+size 2669070720