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
+KULLM3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+KULLM3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

KULLM3-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e43b9924de7c93d3a780c3b2692122d2c3acb18a278dd06e50d6fa2e3af9e5e
+size 4003234016

KULLM3-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65793fcf28d62e14384b165f0b8eaf401a63da4f4a3b75c559801eff53512d87
+size 5650751712

KULLM3-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bffce6bee57618fb7e32f0624497e3eb1a74b0a74f1fffb0bfa0ac7174129ead
+size 5195669728

KULLM3-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6484d04c63055fb7f72d047fa7c98c418c6c067bccbe22e97d7d907098c4e0
+size 4664565984

KULLM3-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed440613c6814bb74d8724c4d7f95dc5f4836b8075cfe4e252c54d05208e74c2
+size 6072385760

KULLM3-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c094541ee3f3d83f543b4ae6f1f420e3ab50d94d61ece85fd7d6a883662897ca
+size 6461669600

KULLM3-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38432f7c2c6f855f106d62b1af77a53011a087631fa60458f72c3f94f74ff8a2
+size 6118523104

KULLM3-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1026dae4e087c5aafe501d3e5fb72ad88d835eaadd9e753872ce9e4f4fb0f19c
+size 7397392608

KULLM3-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b1647bb73dfbdcda0b92c2042770d01d2a6e64dc2794ef2c00db9041eaeede
+size 7597932768

KULLM3-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2c37d1f43f04d07a813bd429fb4528491df74d13ca6df2f2258d696fdd9b38
+size 7397392608

KULLM3-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0b6672bf8a89d9e8a9db0ab74f1f72b63a44346f4ed53fb193936d34f0bc74
+size 8805212384

KULLM3-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cee794e6f297b0957c23e51bdae7fe1283635ed379278b46c6316171d203f8f
+size 11404157152

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+language:
+- en
+- ko
+base_model: nlpai-lab/KULLM3
+tags:
+- TensorBlock
+- GGUF
+---
+
+<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>
+
+## nlpai-lab/KULLM3 - GGUF
+
+This repo contains GGUF format model files for [nlpai-lab/KULLM3](https://huggingface.co/nlpai-lab/KULLM3).
+
+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
+
+```
+<s>[INST] <<SYS>>
+{system_prompt}
+<</SYS>>
+
+{prompt} [/INST]
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [KULLM3-Q2_K.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q2_K.gguf) | Q2_K | 3.728 GB | smallest, significant quality loss - not recommended for most purposes |
+| [KULLM3-Q3_K_S.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q3_K_S.gguf) | Q3_K_S | 4.344 GB | very small, high quality loss |
+| [KULLM3-Q3_K_M.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q3_K_M.gguf) | Q3_K_M | 4.839 GB | very small, high quality loss |
+| [KULLM3-Q3_K_L.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q3_K_L.gguf) | Q3_K_L | 5.263 GB | small, substantial quality loss |
+| [KULLM3-Q4_0.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q4_0.gguf) | Q4_0 | 5.655 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [KULLM3-Q4_K_S.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q4_K_S.gguf) | Q4_K_S | 5.698 GB | small, greater quality loss |
+| [KULLM3-Q4_K_M.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q4_K_M.gguf) | Q4_K_M | 6.018 GB | medium, balanced quality - recommended |
+| [KULLM3-Q5_0.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q5_0.gguf) | Q5_0 | 6.889 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [KULLM3-Q5_K_S.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q5_K_S.gguf) | Q5_K_S | 6.889 GB | large, low quality loss - recommended |
+| [KULLM3-Q5_K_M.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q5_K_M.gguf) | Q5_K_M | 7.076 GB | large, very low quality loss - recommended |
+| [KULLM3-Q6_K.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q6_K.gguf) | Q6_K | 8.200 GB | very large, extremely low quality loss |
+| [KULLM3-Q8_0.gguf](https://huggingface.co/tensorblock/KULLM3-GGUF/tree/main/KULLM3-Q8_0.gguf) | Q8_0 | 10.621 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/KULLM3-GGUF --include "KULLM3-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/KULLM3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```