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
+granite-3.0-3b-a800m-base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-3b-a800m-base-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,177 @@
+---
+pipeline_tag: text-generation
+inference: false
+license: apache-2.0
+library_name: transformers
+tags:
+- language
+- granite-3.0
+- TensorBlock
+- GGUF
+base_model: ibm-granite/granite-3.0-3b-a800m-base
+model-index:
+- name: granite-3.0-3b-a800m-base
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MMLU
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 48.64
+      name: pass@1
+    - type: pass@1
+      value: 18.84
+      name: pass@1
+    - type: pass@1
+      value: 23.81
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: WinoGrande
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 65.67
+      name: pass@1
+    - type: pass@1
+      value: 42.2
+      name: pass@1
+    - type: pass@1
+      value: 47.39
+      name: pass@1
+    - type: pass@1
+      value: 78.29
+      name: pass@1
+    - type: pass@1
+      value: 72.79
+      name: pass@1
+    - type: pass@1
+      value: 41.34
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 75.75
+      name: pass@1
+    - type: pass@1
+      value: 20.96
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 46.84
+      name: pass@1
+    - type: pass@1
+      value: 24.83
+      name: pass@1
+    - type: pass@1
+      value: 38.93
+      name: pass@1
+    - type: pass@1
+      value: 35.05
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: code
+    metrics:
+    - type: pass@1
+      value: 26.83
+      name: pass@1
+    - type: pass@1
+      value: 34.6
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 35.86
+      name: pass@1
+    - type: pass@1
+      value: 17.4
+      name: pass@1
+---
+
+<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>
+
+## ibm-granite/granite-3.0-3b-a800m-base - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-3b-a800m-base](https://huggingface.co/ibm-granite/granite-3.0-3b-a800m-base).
+
+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).
+
+<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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-3.0-3b-a800m-base-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q2_K.gguf) | Q2_K | 1.266 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-3b-a800m-base-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q3_K_S.gguf) | Q3_K_S | 1.488 GB | very small, high quality loss |
+| [granite-3.0-3b-a800m-base-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q3_K_M.gguf) | Q3_K_M | 1.644 GB | very small, high quality loss |
+| [granite-3.0-3b-a800m-base-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q3_K_L.gguf) | Q3_K_L | 1.774 GB | small, substantial quality loss |
+| [granite-3.0-3b-a800m-base-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q4_0.gguf) | Q4_0 | 1.926 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-3b-a800m-base-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q4_K_S.gguf) | Q4_K_S | 1.942 GB | small, greater quality loss |
+| [granite-3.0-3b-a800m-base-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q4_K_M.gguf) | Q4_K_M | 2.059 GB | medium, balanced quality - recommended |
+| [granite-3.0-3b-a800m-base-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q5_0.gguf) | Q5_0 | 2.338 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-3b-a800m-base-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q5_K_S.gguf) | Q5_K_S | 2.338 GB | large, low quality loss - recommended |
+| [granite-3.0-3b-a800m-base-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q5_K_M.gguf) | Q5_K_M | 2.407 GB | large, very low quality loss - recommended |
+| [granite-3.0-3b-a800m-base-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q6_K.gguf) | Q6_K | 2.776 GB | very large, extremely low quality loss |
+| [granite-3.0-3b-a800m-base-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-base-GGUF/blob/main/granite-3.0-3b-a800m-base-Q8_0.gguf) | Q8_0 | 3.593 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/granite-3.0-3b-a800m-base-GGUF --include "granite-3.0-3b-a800m-base-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/granite-3.0-3b-a800m-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3.0-3b-a800m-base-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbf77b0b2403262c52f7505155b9bbdd6fca12338a5a9f088c3c83c167f02b3
+size 1266133088

granite-3.0-3b-a800m-base-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6267a64ff189279a81e1539760b87a62ce821da36d26be3782a5be678a5c7d3f
+size 1773971552

granite-3.0-3b-a800m-base-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8973359555ea996ef9866d268374a2582d071eaf071ecfc14dd99201da481c54
+size 1643620448

granite-3.0-3b-a800m-base-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ed051d55238a8d21df94cf75352a9ddb9968f75ed9f6a14f2ba1eaf1806b97
+size 1488496736

granite-3.0-3b-a800m-base-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0542bc4d8a47c76c591fc6cdb45946c382a549e82cac7b12ef408f11c0bc9a5a
+size 1926342752

granite-3.0-3b-a800m-base-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a081cce3fcfb727a13938dba52cea252c0299b5f09c385b27c92bc578bbf864
+size 2059348064

granite-3.0-3b-a800m-base-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee532d4da901e8a4188b610c6645dae3ed51d4197e68fa5c3bc3c81dc0597c72
+size 1942464608

granite-3.0-3b-a800m-base-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228c29d84108620c91d0cba599ed1ff44ee07b30b9e3a1f4d8f524ace1842894
+size 2338433120

granite-3.0-3b-a800m-base-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b52f61ee41c23ab5d581832355aab41cbf7545e1e444094994a26b440cd1367
+size 2406951008

granite-3.0-3b-a800m-base-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927cd9267ad24c5886dbcd13a95fdf40328e643ae9874dc76c770fa4294848ec
+size 2338433120

granite-3.0-3b-a800m-base-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94afc2b659e97d015ecdb3e41ab2a614b7fa616a9080b2a3141e2b090c958202
+size 2776279136

granite-3.0-3b-a800m-base-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b825f55ea86a32c880f6cdca268e87bd499ef383d12c7ed1571ecdd8e8c9a277
+size 3592988768