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
+reka-flash-3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+reka-flash-3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: RekaAI/reka-flash-3
+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>
+
+## RekaAI/reka-flash-3 - GGUF
+
+This repo contains GGUF format model files for [RekaAI/reka-flash-3](https://huggingface.co/RekaAI/reka-flash-3).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
+
+<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
+
+```
+human: {system_prompt} {prompt} <sep> assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [reka-flash-3-Q2_K.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q2_K.gguf) | Q2_K | 8.631 GB | smallest, significant quality loss - not recommended for most purposes |
+| [reka-flash-3-Q3_K_S.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q3_K_S.gguf) | Q3_K_S | 9.935 GB | very small, high quality loss |
+| [reka-flash-3-Q3_K_M.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q3_K_M.gguf) | Q3_K_M | 10.863 GB | very small, high quality loss |
+| [reka-flash-3-Q3_K_L.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q3_K_L.gguf) | Q3_K_L | 11.412 GB | small, substantial quality loss |
+| [reka-flash-3-Q4_0.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q4_0.gguf) | Q4_0 | 11.924 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [reka-flash-3-Q4_K_S.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q4_K_S.gguf) | Q4_K_S | 12.628 GB | small, greater quality loss |
+| [reka-flash-3-Q4_K_M.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q4_K_M.gguf) | Q4_K_M | 13.610 GB | medium, balanced quality - recommended |
+| [reka-flash-3-Q5_0.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q5_0.gguf) | Q5_0 | 14.460 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [reka-flash-3-Q5_K_S.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q5_K_S.gguf) | Q5_K_S | 14.792 GB | large, low quality loss - recommended |
+| [reka-flash-3-Q5_K_M.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q5_K_M.gguf) | Q5_K_M | 15.635 GB | large, very low quality loss - recommended |
+| [reka-flash-3-Q6_K.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q6_K.gguf) | Q6_K | 18.441 GB | very large, extremely low quality loss |
+| [reka-flash-3-Q8_0.gguf](https://huggingface.co/tensorblock/reka-flash-3-GGUF/blob/main/reka-flash-3-Q8_0.gguf) | Q8_0 | 22.217 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/reka-flash-3-GGUF --include "reka-flash-3-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/reka-flash-3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

reka-flash-3-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b24efb44a5c4ae400c8ef53d3f0b85e1df8fa9a550ff1a53a32c66b600a32a1
+size 8630896128

reka-flash-3-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2823303ddccee9c34f4f1b1d61d14600eaab7e2ed629c813350015a71ef9831a
+size 11412284928

reka-flash-3-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5648b8e4be920711ae3a23b1edbc19b858e3c00c11f4ed3b2066c49e09b0f8
+size 10863011328

reka-flash-3-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c520ef589e308f9aa618dbe8b612bff931f082e7adc6eb16353266d9366404
+size 9934628352

reka-flash-3-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92be1ad6003f46d6b5415ee4f6245f92a03620b898ca74e778e76a9972ecf179
+size 11923736064

reka-flash-3-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3034bede36da5b40a80293497318696066a260566393c460b259cc0c424af876
+size 13610362368

reka-flash-3-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80ce76786dba01fa565a43a0e8a4d14f4e54af039ffb042dc536d10998e0a2d
+size 12627764736

reka-flash-3-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bfabe6dc72f8df1b01bb8c483a47d14352845b39887ac0afc957b7bbaf880c3
+size 14459782656

reka-flash-3-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c0327931ffbcf88949be79cf81301e2ff19212e8d353da90087b2c6b73ba35
+size 15635473920

reka-flash-3-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8d8ccecb975e03e11f406ee8d140a1695c029e0e21d15cdd6b9f0cd9e81aba
+size 14791755264

reka-flash-3-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d3f8e2111adfa977dd97a57f38982dd2caf306926f2f2dcf8c30d19f67671d
+size 18440726016

reka-flash-3-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab6186e19988a9cbdee4ca5794960d25af1936169daf44a353262bdff61f3c6
+size 22217246208