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-3.0-2b-base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-2b-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-3.0-2b-base
+model-index:
+- name: granite-3.0-2b-base
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MMLU
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 55.0
+      name: pass@1
+    - type: pass@1
+      value: 23.79
+      name: pass@1
+    - type: pass@1
+      value: 22.56
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: WinoGrande
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 74.9
+      name: pass@1
+    - type: pass@1
+      value: 43.0
+      name: pass@1
+    - type: pass@1
+      value: 59.84
+      name: pass@1
+    - type: pass@1
+      value: 79.27
+      name: pass@1
+    - type: pass@1
+      value: 77.65
+      name: pass@1
+    - type: pass@1
+      value: 39.9
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 81.35
+      name: pass@1
+    - type: pass@1
+      value: 25.22
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 54.27
+      name: pass@1
+    - type: pass@1
+      value: 30.58
+      name: pass@1
+    - type: pass@1
+      value: 40.69
+      name: pass@1
+    - type: pass@1
+      value: 34.34
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: code
+    metrics:
+    - type: pass@1
+      value: 38.41
+      name: pass@1
+    - type: pass@1
+      value: 35.4
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 47.23
+      name: pass@1
+    - type: pass@1
+      value: 19.46
+      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-3.0-2b-base - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-2b-base](https://huggingface.co/ibm-granite/granite-3.0-2b-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-3.0-2b-base-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q2_K.gguf) | Q2_K | 0.978 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-2b-base-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q3_K_S.gguf) | Q3_K_S | 1.130 GB | very small, high quality loss |
+| [granite-3.0-2b-base-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q3_K_M.gguf) | Q3_K_M | 1.252 GB | very small, high quality loss |
+| [granite-3.0-2b-base-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q3_K_L.gguf) | Q3_K_L | 1.357 GB | small, substantial quality loss |
+| [granite-3.0-2b-base-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q4_0.gguf) | Q4_0 | 1.453 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-2b-base-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q4_K_S.gguf) | Q4_K_S | 1.464 GB | small, greater quality loss |
+| [granite-3.0-2b-base-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q4_K_M.gguf) | Q4_K_M | 1.545 GB | medium, balanced quality - recommended |
+| [granite-3.0-2b-base-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q5_0.gguf) | Q5_0 | 1.757 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-2b-base-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q5_K_S.gguf) | Q5_K_S | 1.757 GB | large, low quality loss - recommended |
+| [granite-3.0-2b-base-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q5_K_M.gguf) | Q5_K_M | 1.805 GB | large, very low quality loss - recommended |
+| [granite-3.0-2b-base-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q6_K.gguf) | Q6_K | 2.081 GB | very large, extremely low quality loss |
+| [granite-3.0-2b-base-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-2b-base-GGUF/blob/main/granite-3.0-2b-base-Q8_0.gguf) | Q8_0 | 2.694 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-3.0-2b-base-GGUF --include "granite-3.0-2b-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-3.0-2b-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3.0-2b-base-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86182099e9ecf15636f8f65d13a3dfc49aace1800809373486ac97ff0312d0e
+size 978236224

granite-3.0-2b-base-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae05515b30e69d1cad5c31674518722885ee6c56c1033913a1b7edfb9e983783
+size 1357361984

granite-3.0-2b-base-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65359e93e4c68fdd15f80bceefce4ee8277263f9069085f1fbf6a6bdf76adef8
+size 1251717952

granite-3.0-2b-base-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7691e3f706553dcf884f9a20dca58034b8b6e9af4d301a11acb1be21b259ffc
+size 1130279744

granite-3.0-2b-base-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa18c26f85f2e2e915d3b4e514b56d77010cec13976f2f7c456d48532422b152
+size 1453372224

granite-3.0-2b-base-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa3c2b93a13036b5487febd709dbdaddcd3e994194935138025d532509312c3
+size 1545286464

granite-3.0-2b-base-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118c27727a26691e26e6d7d18480b6afeb7c99e51824aeccc4c53179a1058d0a
+size 1464382272

granite-3.0-2b-base-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7af441a0d9b7c2f0efbb73e6e012650c474a503a85524b23e2918ebcf54376
+size 1757459264

granite-3.0-2b-base-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca332f92c8b24d0fbe3ff9ceab3f27e1cf5217d71caa46d619588c18fe692849
+size 1804809024

granite-3.0-2b-base-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8884a6f15bc83a3fe99d9526a5fcb2c83c31a8d1d01e705f01295fdade4c9052
+size 1757459264

granite-3.0-2b-base-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de881d7f1803614f3fd4ba17cdf1b16fbec3e524488f853b318c8476a520d0f
+size 2080551744

granite-3.0-2b-base-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4597bb921558641f37882fbc646bff980e8e2e91c62a8a4fe493d3aca06397ff
+size 2694099776