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-3.0-8b-base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-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-3.0-8b-base
+model-index:
+- name: granite-3.0-8b-base
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MMLU
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 65.54
+      name: pass@1
+    - type: pass@1
+      value: 33.27
+      name: pass@1
+    - type: pass@1
+      value: 34.45
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: WinoGrande
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 80.9
+      name: pass@1
+    - type: pass@1
+      value: 46.8
+      name: pass@1
+    - type: pass@1
+      value: 67.8
+      name: pass@1
+    - type: pass@1
+      value: 82.32
+      name: pass@1
+    - type: pass@1
+      value: 83.61
+      name: pass@1
+    - type: pass@1
+      value: 52.89
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 86.97
+      name: pass@1
+    - type: pass@1
+      value: 32.92
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 63.4
+      name: pass@1
+    - type: pass@1
+      value: 32.13
+      name: pass@1
+    - type: pass@1
+      value: 49.31
+      name: pass@1
+    - type: pass@1
+      value: 41.08
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: code
+    metrics:
+    - type: pass@1
+      value: 52.44
+      name: pass@1
+    - type: pass@1
+      value: 41.4
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 64.06
+      name: pass@1
+    - type: pass@1
+      value: 29.28
+      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-3.0-8b-base - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-8b-base](https://huggingface.co/ibm-granite/granite-3.0-8b-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-3.0-8b-base-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q2_K.gguf) | Q2_K | 3.104 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-8b-base-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q3_K_S.gguf) | Q3_K_S | 3.592 GB | very small, high quality loss |
+| [granite-3.0-8b-base-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q3_K_M.gguf) | Q3_K_M | 3.997 GB | very small, high quality loss |
+| [granite-3.0-8b-base-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q3_K_L.gguf) | Q3_K_L | 4.349 GB | small, substantial quality loss |
+| [granite-3.0-8b-base-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q4_0.gguf) | Q4_0 | 4.651 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-8b-base-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q4_K_S.gguf) | Q4_K_S | 4.686 GB | small, greater quality loss |
+| [granite-3.0-8b-base-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q4_K_M.gguf) | Q4_K_M | 4.943 GB | medium, balanced quality - recommended |
+| [granite-3.0-8b-base-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q5_0.gguf) | Q5_0 | 5.647 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-8b-base-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q5_K_S.gguf) | Q5_K_S | 5.647 GB | large, low quality loss - recommended |
+| [granite-3.0-8b-base-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q5_K_M.gguf) | Q5_K_M | 5.797 GB | large, very low quality loss - recommended |
+| [granite-3.0-8b-base-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q6_K.gguf) | Q6_K | 6.705 GB | very large, extremely low quality loss |
+| [granite-3.0-8b-base-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-base-GGUF/blob/main/granite-3.0-8b-base-Q8_0.gguf) | Q8_0 | 8.684 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-3.0-8b-base-GGUF --include "granite-3.0-8b-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-3.0-8b-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3.0-8b-base-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38939ddd92c30daa93f9a2c7ab54a87466975fa192a9dabafbfd9d1b5964280
+size 3103576896

granite-3.0-8b-base-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e9fdb4f48d9351a364ba292484ede897b8779f0f179d02cecbfaa71d0bccfe
+size 4349416256

granite-3.0-8b-base-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcf256b80f8256df1e4d04932ab468fec69b19629db4fca17b4118008617f43
+size 3996570432

granite-3.0-8b-base-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f4c56422a8775edb27cb932d7d5c8fcad37a2fe91c9c6a884902ee730b4784
+size 3592475456

granite-3.0-8b-base-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cef65719c2445551885ab3359031ba84caffd47bd4becd14793b30ed5ba241
+size 4650881856

granite-3.0-8b-base-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a1692434a2b2b35cf512e722646b5d46b849a1f74ee007c950e62346c22486
+size 4942844736

granite-3.0-8b-base-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34178ff0ff8f340f57b3d0fb9e9305748c29fd9769d40c92cba9d4b2fcf29573
+size 4685747008

granite-3.0-8b-base-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2f84052022d89c21db898d79e8055874b310866e49d6121e9e54b2e7fb645f
+size 5647029056

granite-3.0-8b-base-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8700068686021141a758a714242be40a7c62a3c1a43277f93ad0349692b6ed9
+size 5797434176

granite-3.0-8b-base-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e9e97b36236317656db15bea02f8f28a30955b86118cba751fa238e010a9f05
+size 5647029056

granite-3.0-8b-base-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e2eee298b731dbbddc71672cc694d909b4ce9af9711d203898dd8d2a470853
+size 6705435456

granite-3.0-8b-base-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24ad18cca054f5e4d8b651150878e8047202804cd27c3d6ba17a2bd3f20c1ae
+size 8684229440