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
+CompassJudger-1-32B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+CompassJudger-1-32B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

CompassJudger-1-32B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c6aaa38b60251669d22d70611bfb115cdfdea96bc92d0b7d799ece98bfc57b
+size 12313098720

CompassJudger-1-32B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed573e68db6ee6fe74e610b6bd8c7dbc727acbf49209045d6a2520ec51a7327
+size 17247078880

CompassJudger-1-32B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582c4ae5569e8f32e65a531d735b18a18020307bfd914a262349f2918a56c884
+size 15935048160

CompassJudger-1-32B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2d5c5f15f8015b9c7e626cc1048af3b3ae6bfe43a8a0be84d4c68ef4a858aa
+size 14392330720

CompassJudger-1-32B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403b8e78eb45a48be3e4ba5337f724c50913fe159b7d1d3d8373b89dc2e82438
+size 18640230880

CompassJudger-1-32B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5572e4292b5dd715d0cc388abd34e2c44fe6b0698b96221e200f956d6af8f45
+size 19851336160

CompassJudger-1-32B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cadf73ec24adf0fbcfa9f44caa871f53a76cf4ee610a1c8084d9c0f04f92e60
+size 18784410080

CompassJudger-1-32B-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef19c15743c6dc88b873560f69e4e9af796def02b1a2caf420cdaa30bafa7728
+size 22638254560

CompassJudger-1-32B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7571cf64496a3aab399dfaa5bb1cba6bb0549ef6c4654391eaf844f3d25d3acd
+size 23262157280

CompassJudger-1-32B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94dc35479af9d11e314abb1598af7fa9f3fe7aba37d2cf159bf2068d6047e6a
+size 22638254560

CompassJudger-1-32B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec98a66c48de8b1b68d2c14569a1bc9deedded1f9760b3c58378b08106087ff
+size 26886154720

CompassJudger-1-32B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554aed06e53e3fb1279796e54b9ae294e770262a904c53b7cddde2378797bb21
+size 34820884960

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: opencompass/CompassJudger-1-32B-Instruct
+library_name: transformers
+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>
+
+## opencompass/CompassJudger-1-32B-Instruct - GGUF
+
+This repo contains GGUF format model files for [opencompass/CompassJudger-1-32B-Instruct](https://huggingface.co/opencompass/CompassJudger-1-32B-Instruct).
+
+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).
+
+<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
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [CompassJudger-1-32B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
+| [CompassJudger-1-32B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
+| [CompassJudger-1-32B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
+| [CompassJudger-1-32B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
+| [CompassJudger-1-32B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [CompassJudger-1-32B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
+| [CompassJudger-1-32B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
+| [CompassJudger-1-32B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [CompassJudger-1-32B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
+| [CompassJudger-1-32B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
+| [CompassJudger-1-32B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
+| [CompassJudger-1-32B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/CompassJudger-1-32B-Instruct-GGUF/blob/main/CompassJudger-1-32B-Instruct-Q8_0.gguf) | Q8_0 | 34.821 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/CompassJudger-1-32B-Instruct-GGUF --include "CompassJudger-1-32B-Instruct-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/CompassJudger-1-32B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```