Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ 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
+OpenMath2-Llama3.1-70B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q6_K/OpenMath2-Llama3.1-70B-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q6_K/OpenMath2-Llama3.1-70B-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q8_0/OpenMath2-Llama3.1-70B-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q8_0/OpenMath2-Llama3.1-70B-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+OpenMath2-Llama3.1-70B-Q8_0/OpenMath2-Llama3.1-70B-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

OpenMath2-Llama3.1-70B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885bffd60a1e9b490d7e71434aa150163e8d9a29af9b66b216a7a6c87f3e8083
+size 26375113376

OpenMath2-Llama3.1-70B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132744862d307bece4acfaef4e6e22d448bb4aa9567395d27d10fc3c98cfb90c
+size 37140597408

OpenMath2-Llama3.1-70B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe41b861639d27880754e9c08da5e7b0cfacb36baa1dddacb707cc1d539040b
+size 34267499168

OpenMath2-Llama3.1-70B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98aa4add5c2e27be8fc8d771dcf006ccd5e760425c5852a07783b51f2b8a044
+size 30912055968

OpenMath2-Llama3.1-70B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b6a3c83bdf8b3fa807988fa76c25d04a26322fe3508a3226bcee64c018599b
+size 39969737376

OpenMath2-Llama3.1-70B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570ee5cc210f872de347b5f558fc0768d5bc84464195353eb70456de21ad573b
+size 42520398496

OpenMath2-Llama3.1-70B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2413703a7289671583d7e93cdcaba05246671bd49def0c3def8b2eb2e41b549f
+size 40347224736

OpenMath2-Llama3.1-70B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a39d612826fb31dc07d169ba49804ede6662a81e78d741c8410bac1d65c17e
+size 48657451680

OpenMath2-Llama3.1-70B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0c7f0b80e765307a00cb345596c5119feeed3cbf415f51a555e331fa669a75
+size 49949821600

OpenMath2-Llama3.1-70B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5c980c3dcd74abcd194fbf0d48d09f3c7e33c8217f6f445d8dadf36d2c8ce3
+size 48657451680

OpenMath2-Llama3.1-70B-Q6_K/OpenMath2-Llama3.1-70B-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bf3c68c288f1f7da71cceaebc16d00b54e8299acfc5a590ec0d6364c1d558f
+size 34847475392

OpenMath2-Llama3.1-70B-Q6_K/OpenMath2-Llama3.1-70B-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b46e6dcd09f82e2320f7deb743f18f6a65bf3993b4e31cc065752dfb5982df76
+size 23040672928

OpenMath2-Llama3.1-70B-Q8_0/OpenMath2-Llama3.1-70B-Q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bcd3452ed633c6d4ed481be258b9cca7f560c4d9606e31ae7675513e025ef6
+size 34980015840

OpenMath2-Llama3.1-70B-Q8_0/OpenMath2-Llama3.1-70B-Q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73ffed29875bbb72fcfdc2b23fba8a6078e17cb3b7e425adcf72ea90a7344fd
+size 34949976384

OpenMath2-Llama3.1-70B-Q8_0/OpenMath2-Llama3.1-70B-Q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c154178cfcbbd28a520130bdb57c077b0a3f7ccb130d25118b3e47be63c96c3
+size 5045062560

README.md

@@ -0,0 +1,87 @@
+---
+license: llama3.1
+base_model: nvidia/OpenMath2-Llama3.1-70B
+datasets:
+- nvidia/OpenMathInstruct-2
+language:
+- en
+tags:
+- nvidia
+- math
+- TensorBlock
+- GGUF
+library_name: transformers
+---
+
+<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>
+
+## nvidia/OpenMath2-Llama3.1-70B - GGUF
+
+This repo contains GGUF format model files for [nvidia/OpenMath2-Llama3.1-70B](https://huggingface.co/nvidia/OpenMath2-Llama3.1-70B).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit ec7f3ac](https://github.com/ggerganov/llama.cpp/commit/ec7f3ac9ab33e46b136eb5ab6a76c4d81f57c7f1).
+
+<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
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [OpenMath2-Llama3.1-70B-Q2_K.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
+| [OpenMath2-Llama3.1-70B-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
+| [OpenMath2-Llama3.1-70B-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
+| [OpenMath2-Llama3.1-70B-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
+| [OpenMath2-Llama3.1-70B-Q4_0.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [OpenMath2-Llama3.1-70B-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
+| [OpenMath2-Llama3.1-70B-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
+| [OpenMath2-Llama3.1-70B-Q5_0.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [OpenMath2-Llama3.1-70B-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
+| [OpenMath2-Llama3.1-70B-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
+| [OpenMath2-Llama3.1-70B-Q6_K](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
+| [OpenMath2-Llama3.1-70B-Q8_0](https://huggingface.co/tensorblock/OpenMath2-Llama3.1-70B-GGUF/blob/main/OpenMath2-Llama3.1-70B-Q8_0) | Q8_0 | 74.975 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/OpenMath2-Llama3.1-70B-GGUF --include "OpenMath2-Llama3.1-70B-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/OpenMath2-Llama3.1-70B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```