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
+MegaBeam-Mistral-7B-512k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+MegaBeam-Mistral-7B-512k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

MegaBeam-Mistral-7B-512k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f4d45346d1a8ca382711c6681e4c88b8a100a8e89f123863a15d5962d92d42
+size 2719242880

MegaBeam-Mistral-7B-512k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2197b312d1721b93bcb44689516d0003b9ba574ff48646e703c387e5d165fea
+size 3822025344

MegaBeam-Mistral-7B-512k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285c6d0b8ffe8bbea59bc60ff494717b7a9ef0eda73ce0cfc066bc84c0d24224
+size 3518986880

MegaBeam-Mistral-7B-512k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc547209fb74af691a9a7037e0e1bc92743405c9182124885198f8880cec186e
+size 3164568192

MegaBeam-Mistral-7B-512k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4458d993fcaf364609b0b417745d85e6c5434e7cd83522aef7d47d5194e648a3
+size 4108917376

MegaBeam-Mistral-7B-512k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7ac0734372db83d87f183396de183145e197b3e4535995278fa0863865732f
+size 4368439936

MegaBeam-Mistral-7B-512k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09474a94826020089c44876b5c78e98c1825b7f27ee691d217ad677dbfe3487e
+size 4140374656

MegaBeam-Mistral-7B-512k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e3397018f27b0a52781da687f88f61311abbe3c1de2da9e3421281d5f9977b
+size 4997716608

MegaBeam-Mistral-7B-512k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51cbb36e33f737ff556488f7e71ec5ebe2937f55be60454eeb42bc9842c5d29
+size 5131410048

MegaBeam-Mistral-7B-512k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b235a00ca2608f03fe65cdf298e0ece00365fe5838c42e0362b074d49f3c4fed
+size 4997716608

MegaBeam-Mistral-7B-512k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467677afa9b027a7266b932d4b5694b7866aa3e8022178af8e9941b8cf80def7
+size 5942065792

MegaBeam-Mistral-7B-512k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f940748c3225baad199e700216267c3c7a442173c97a618518fcfdb2a596bbf
+size 7695858304

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+inference: false
+base_model: aws-prototyping/MegaBeam-Mistral-7B-512k
+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>
+
+## aws-prototyping/MegaBeam-Mistral-7B-512k - GGUF
+
+This repo contains GGUF format model files for [aws-prototyping/MegaBeam-Mistral-7B-512k](https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k).
+
+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>[INST] {prompt} [/INST]
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [MegaBeam-Mistral-7B-512k-Q2_K.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [MegaBeam-Mistral-7B-512k-Q3_K_S.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [MegaBeam-Mistral-7B-512k-Q3_K_M.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [MegaBeam-Mistral-7B-512k-Q3_K_L.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [MegaBeam-Mistral-7B-512k-Q4_0.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [MegaBeam-Mistral-7B-512k-Q4_K_S.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [MegaBeam-Mistral-7B-512k-Q4_K_M.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [MegaBeam-Mistral-7B-512k-Q5_0.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [MegaBeam-Mistral-7B-512k-Q5_K_S.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [MegaBeam-Mistral-7B-512k-Q5_K_M.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [MegaBeam-Mistral-7B-512k-Q6_K.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [MegaBeam-Mistral-7B-512k-Q8_0.gguf](https://huggingface.co/tensorblock/MegaBeam-Mistral-7B-512k-GGUF/tree/main/MegaBeam-Mistral-7B-512k-Q8_0.gguf) | Q8_0 | 7.167 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/MegaBeam-Mistral-7B-512k-GGUF --include "MegaBeam-Mistral-7B-512k-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/MegaBeam-Mistral-7B-512k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```