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
+Moxoff-Phi3Mini-PPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Moxoff-Phi3Mini-PPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Moxoff-Phi3Mini-PPO-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab78c4c65020de7690e4d2ddc5042b20e96e211c053f691e1dc8b9e7a18684b
+size 1416204160

Moxoff-Phi3Mini-PPO-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96115efc7e3f2fbd0cfa2cf7f9e5e6c19a41a7b81be5ec1db0fe7f7ddc54579b
+size 2087597440

Moxoff-Phi3Mini-PPO-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a00aedc3c79ae2639e125abc3476ac3d52da3bd99fa587731d73a5c184732a1
+size 1955476864

Moxoff-Phi3Mini-PPO-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7ab3e5b8ec7ca7af38f8a03f46559a68df4afcf417d1651954ba243733b569
+size 1681798528

Moxoff-Phi3Mini-PPO-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981ad536be6cd1623ad7d1b040ef6087e5b280e14faa3712ff8b02543751e3cd
+size 2176177024

Moxoff-Phi3Mini-PPO-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23258f050737e989b2874c1a417f650d730d76c823e3ec339e6f49fbf7ede9e
+size 2393232256

Moxoff-Phi3Mini-PPO-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e24921f719387ecf98c2ac5c5600a081e296413661d955c2ae5d7388df1fb4f
+size 2188759936

Moxoff-Phi3Mini-PPO-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431f8d4af78bb1c1362cb5470a14b8bfcf46160f2c147d6c52053ef3246b6c43
+size 2641474432

Moxoff-Phi3Mini-PPO-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f99fcf3b10a870848218cc4ad6e9b226b455c339496e8a1cc5eeb3b737ccca
+size 2815275904

Moxoff-Phi3Mini-PPO-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb981157741aa5555c613748d99477310ce406dc026143017cd1c267e46868bc
+size 2641474432

Moxoff-Phi3Mini-PPO-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cd62c0adeac4450674eb7dd031d4ecf5e05aad91230ed87373f2fa1a435b72
+size 3135852928

Moxoff-Phi3Mini-PPO-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f755ddf055603044c07dfeeeffaabbd0a518f3fa04208c4319aeea81dc3946
+size 4061222272

README.md

@@ -0,0 +1,83 @@
+---
+license: mit
+language:
+- en
+library_name: transformers
+tags:
+- ppo
+- phi3
+- chatml
+- TensorBlock
+- GGUF
+datasets: argilla/ultrafeedback-binarized-preferences-cleaned
+metrics:
+- hellaswag
+- arc_challenge
+- m_mmlu 5 shot
+base_model: MoxoffSpA/Moxoff-Phi3Mini-PPO
+---
+
+<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>
+
+## MoxoffSpA/Moxoff-Phi3Mini-PPO - GGUF
+
+This repo contains GGUF format model files for [MoxoffSpA/Moxoff-Phi3Mini-PPO](https://huggingface.co/MoxoffSpA/Moxoff-Phi3Mini-PPO).
+
+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><|user|>
+{prompt}<|end|>
+<|assistant|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Moxoff-Phi3Mini-PPO-Q2_K.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q2_K.gguf) | Q2_K | 1.319 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Moxoff-Phi3Mini-PPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q3_K_S.gguf) | Q3_K_S | 1.566 GB | very small, high quality loss |
+| [Moxoff-Phi3Mini-PPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q3_K_M.gguf) | Q3_K_M | 1.821 GB | very small, high quality loss |
+| [Moxoff-Phi3Mini-PPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q3_K_L.gguf) | Q3_K_L | 1.944 GB | small, substantial quality loss |
+| [Moxoff-Phi3Mini-PPO-Q4_0.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q4_0.gguf) | Q4_0 | 2.027 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Moxoff-Phi3Mini-PPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q4_K_S.gguf) | Q4_K_S | 2.038 GB | small, greater quality loss |
+| [Moxoff-Phi3Mini-PPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q4_K_M.gguf) | Q4_K_M | 2.229 GB | medium, balanced quality - recommended |
+| [Moxoff-Phi3Mini-PPO-Q5_0.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q5_0.gguf) | Q5_0 | 2.460 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Moxoff-Phi3Mini-PPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q5_K_S.gguf) | Q5_K_S | 2.460 GB | large, low quality loss - recommended |
+| [Moxoff-Phi3Mini-PPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q5_K_M.gguf) | Q5_K_M | 2.622 GB | large, very low quality loss - recommended |
+| [Moxoff-Phi3Mini-PPO-Q6_K.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q6_K.gguf) | Q6_K | 2.920 GB | very large, extremely low quality loss |
+| [Moxoff-Phi3Mini-PPO-Q8_0.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-PPO-GGUF/tree/main/Moxoff-Phi3Mini-PPO-Q8_0.gguf) | Q8_0 | 3.782 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/Moxoff-Phi3Mini-PPO-GGUF --include "Moxoff-Phi3Mini-PPO-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/Moxoff-Phi3Mini-PPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```