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

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+tags:
+- TensorBlock
+- GGUF
+base_model: PKU-ONELab/Themis
+---
+
+<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>
+
+## PKU-ONELab/Themis - GGUF
+
+This repo contains GGUF format model files for [PKU-ONELab/Themis](https://huggingface.co/PKU-ONELab/Themis).
+
+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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Themis-Q2_K.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Themis-Q3_K_S.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [Themis-Q3_K_M.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [Themis-Q3_K_L.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [Themis-Q4_0.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Themis-Q4_K_S.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [Themis-Q4_K_M.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [Themis-Q5_0.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Themis-Q5_K_S.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [Themis-Q5_K_M.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [Themis-Q6_K.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [Themis-Q8_0.gguf](https://huggingface.co/tensorblock/Themis-GGUF/tree/main/Themis-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/Themis-GGUF --include "Themis-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/Themis-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Themis-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b296cb4392e7f0f61a0df67477e5b59e3f0a235d38d19ab1f35e2f3fd848718
+size 3179130944

Themis-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b73ed1baa1a449ef1b9a83af59c01225b70538a588f095a33cc2da7543cfa03
+size 4321955904

Themis-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf77c38fb9c90aec0c2f337d523eb0abe1d35b4baeb6263f9f6e6ea4b980d7f
+size 4018917440

Themis-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b668da3cf68f9cd2efe2f4e4b1da6df1d8e75f5e0f23c6712ee830f994acc3
+size 3664498752

Themis-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6d05383c6ac70a63ed7fe502d4e2cb7af2f2f9c6a46a054472bc756db2304e
+size 4661211200

Themis-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd26d0eecae111f6de435450809d24e2eddd11b633467baec3451e277e2021d
+size 4920733760

Themis-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb78c0eaea368950f518dbdf736a2624e9ecd4b9df8aedd0f689b5c6c3aba2fc
+size 4692668480

Themis-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570f992e0c4a0009c8a689b7485eae9dbf7b6111a41d10210282d9a7a5711116
+size 5599293504

Themis-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c7f6414a15f760479051e55eec851001d42498aaf7c58842dc1f52c4ff65bd
+size 5732986944

Themis-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b8b792f472df87411346d46125871d1d4d23592ef7156b4bf2edb9d1774ebd
+size 5599293504

Themis-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8413e1c151b72995ac45d09320dfb4f2b2a5f2668553c9062238e72f107f1960
+size 6596005952

Themis-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb2bfe010adb56da2f75c171571ab45c5382b5dcd19bda7adcf6716af9af50b
+size 8540770368