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
+phi-2-4bit-64rank-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+phi-2-4bit-64rank-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- 'quantization '
+- lora
+- TensorBlock
+- GGUF
+base_model: LoftQ/phi-2-4bit-64rank
+---
+
+<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>
+
+## LoftQ/phi-2-4bit-64rank - GGUF
+
+This repo contains GGUF format model files for [LoftQ/phi-2-4bit-64rank](https://huggingface.co/LoftQ/phi-2-4bit-64rank).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [phi-2-4bit-64rank-Q2_K.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q2_K.gguf) | Q2_K | 1.110 GB | smallest, significant quality loss - not recommended for most purposes |
+| [phi-2-4bit-64rank-Q3_K_S.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q3_K_S.gguf) | Q3_K_S | 1.251 GB | very small, high quality loss |
+| [phi-2-4bit-64rank-Q3_K_M.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q3_K_M.gguf) | Q3_K_M | 1.426 GB | very small, high quality loss |
+| [phi-2-4bit-64rank-Q3_K_L.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q3_K_L.gguf) | Q3_K_L | 1.575 GB | small, substantial quality loss |
+| [phi-2-4bit-64rank-Q4_0.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q4_0.gguf) | Q4_0 | 1.602 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [phi-2-4bit-64rank-Q4_K_S.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q4_K_S.gguf) | Q4_K_S | 1.619 GB | small, greater quality loss |
+| [phi-2-4bit-64rank-Q4_K_M.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q4_K_M.gguf) | Q4_K_M | 1.738 GB | medium, balanced quality - recommended |
+| [phi-2-4bit-64rank-Q5_0.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q5_0.gguf) | Q5_0 | 1.933 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [phi-2-4bit-64rank-Q5_K_S.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q5_K_S.gguf) | Q5_K_S | 1.933 GB | large, low quality loss - recommended |
+| [phi-2-4bit-64rank-Q5_K_M.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q5_K_M.gguf) | Q5_K_M | 2.003 GB | large, very low quality loss - recommended |
+| [phi-2-4bit-64rank-Q6_K.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q6_K.gguf) | Q6_K | 2.285 GB | very large, extremely low quality loss |
+| [phi-2-4bit-64rank-Q8_0.gguf](https://huggingface.co/tensorblock/phi-2-4bit-64rank-GGUF/blob/main/phi-2-4bit-64rank-Q8_0.gguf) | Q8_0 | 2.958 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/phi-2-4bit-64rank-GGUF --include "phi-2-4bit-64rank-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/phi-2-4bit-64rank-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

phi-2-4bit-64rank-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e7f07f321a41a2c053511944df2c2f2006bc2e68f02285da8acede0593e1a0
+size 1109720064

phi-2-4bit-64rank-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb679044596d808bd85d6de90c12f19fdad382268d89cc6c46e00948f18096a
+size 1575230464

phi-2-4bit-64rank-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82659ff04353d9c28705c0bb4abc5da648e87d0a02c7ff8f0b858c78dc5f35b2
+size 1426136064

phi-2-4bit-64rank-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eabe04823fb904c2efb6cb728cd0e99ef44e0792a3835229d091fb4ca86a68f
+size 1250827264

phi-2-4bit-64rank-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6774c637ce62e3557c77d4a1856c67160b123d564b3ecda45a0cbd2ee881e097
+size 1602468864

phi-2-4bit-64rank-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6ba49e85922d3f3da775fd1cf712bb3ab73afe9623f4701b2f8b6e80b5af21
+size 1737636864

phi-2-4bit-64rank-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa4824567c25580eeb4adfd7e79ac7320653d02ad4b29aca88d3433929acf88
+size 1618852864

phi-2-4bit-64rank-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e40b5dd9c2eecf3afee6c4f3c5db627f2d9d14c302e3090cf454726b94a4406
+size 1933425664

phi-2-4bit-64rank-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d55185543a08a3ad994dbd6a4b4d38a198f50ade4b8b386c9a3ef65c8f82495
+size 2003057664

phi-2-4bit-64rank-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b488e18439fef4b1c252c83ff5d796249168bf3df60bba4b268acd05c49abbc
+size 1933425664

phi-2-4bit-64rank-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188da3fc92216591ec2a2a2f12085ed592cd065a7a9bdcf3d2d1e654750ab4b9
+size 2285067264

phi-2-4bit-64rank-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c20637ea5a0daf124e79e29d9b7da696d57facccbfe2946023133362d389be8
+size 2958040064