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
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f493aad4d936febcb502502c527fedc417bda45333c59e4eb31ee2ca209b8b7b
+size 26375113504

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16692a664d24e6dbeeee959050772b7568cb81fc28ff35455d6b344dddcc98aa
+size 37140597536

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c37f38559a45d7e79345498b1936ab2ccb1a4fc9a8c24a406c415dc154d74f0
+size 34267499296

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e062bac083c718ca1761cab224c53f0fd5c13f229e3db713803ba884e4978c
+size 30912056096

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e8f3b0f349d9a6ac16a6f7955f041675787900b6c370de377f94e79202d981b
+size 39969737504

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74599610d7fd0de163e45844c91522f5b0f87e5c00bc8e4a25992b61d80b0aa2
+size 42520398624

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1471bcd4666c844b54c1f633bbeb3f6f7b9adf065477b9eded206cbc5c96fe25
+size 40347224864

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae4a0866b84c3b5172ce50e785bba6ef82de09e9ecd7e544ea14ed1208f43a4
+size 48657451808

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ad5e8e57738cef6c5f1e745278cdd211bf82880ab29d858e5de1f2a1b179f2
+size 49949821728

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe42ec583ac63f273757b8f45e0b4abeeb3f94c9b0bdfeafca6394ea1f5a6d0d
+size 48657451808

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2625d1ce37286f85f129204037c259d57293be202bb9dc719c9acbc55e207164
+size 34847475520

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc444ac74642c720688cb35bba591e9a280f84bd676357b5e424d8b58182c581
+size 23040672928

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1161ac1969c050f7468bfc7d4e05d788e53d186272830f0ffa9f252d9088b9ec
+size 34980016000

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac85549e0f47ab191966eb4ba948c4db10469d490de8307c4e68790ca4c9396
+size 34949976384

Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70bb1fd4350d15d937f647e1c7b946b09020c428e028cf9ff538db006135416c
+size 5045062560

README.md

@@ -0,0 +1,91 @@
+---
+base_model: mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16
+datasets:
+- nvidia/HelpSteer2
+language:
+- en
+library_name: transformers
+license: llama3.1
+pipeline_tag: text-generation
+tags:
+- nvidia
+- llama3.1
+- mlx
+- TensorBlock
+- GGUF
+inference: false
+fine-tuning: false
+---
+
+<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>
+
+## mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16 - GGUF
+
+This repo contains GGUF format model files for [mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16](https://huggingface.co/mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16).
+
+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
+
+```
+<|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 |
+| -------- | ---------- | --------- | ----------- |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
+| [Llama-3.1-Nemotron-70B-Instruct-HF-bf16-Q8_0](https://huggingface.co/tensorblock/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF/blob/main/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-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/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF --include "Llama-3.1-Nemotron-70B-Instruct-HF-bf16-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/Llama-3.1-Nemotron-70B-Instruct-HF-bf16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```