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

README.md

@@ -0,0 +1,203 @@
+---
+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-instruct
+model-index:
+- name: granite-3.0-2b-instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: IFEval
+      type: instruction-following
+    metrics:
+    - type: pass@1
+      value: 42.49
+      name: pass@1
+    - type: pass@1
+      value: 7.02
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: AGI-Eval
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 25.7
+      name: pass@1
+    - type: pass@1
+      value: 50.16
+      name: pass@1
+    - type: pass@1
+      value: 20.51
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: OBQA
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 40.8
+      name: pass@1
+    - type: pass@1
+      value: 59.95
+      name: pass@1
+    - type: pass@1
+      value: 71.86
+      name: pass@1
+    - type: pass@1
+      value: 67.01
+      name: pass@1
+    - type: pass@1
+      value: 48
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 78.65
+      name: pass@1
+    - type: pass@1
+      value: 6.71
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 50.94
+      name: pass@1
+    - type: pass@1
+      value: 26.85
+      name: pass@1
+    - type: pass@1
+      value: 37.7
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis
+      type: code
+    metrics:
+    - type: pass@1
+      value: 39.63
+      name: pass@1
+    - type: pass@1
+      value: 40.85
+      name: pass@1
+    - type: pass@1
+      value: 35.98
+      name: pass@1
+    - type: pass@1
+      value: 27.4
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 47.54
+      name: pass@1
+    - type: pass@1
+      value: 19.86
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: PAWS-X (7 langs)
+      type: multilingual
+    metrics:
+    - type: pass@1
+      value: 50.23
+      name: pass@1
+    - type: pass@1
+      value: 28.87
+      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-instruct - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-3b-a800m-instruct](https://huggingface.co/ibm-granite/granite-3.0-3b-a800m-instruct).
+
+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
+
+```
+<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|>
+<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|>
+<|start_of_role|>assistant<|end_of_role|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-3.0-3b-a800m-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q2_K.gguf) | Q2_K | 1.266 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-3b-a800m-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_S.gguf) | Q3_K_S | 1.489 GB | very small, high quality loss |
+| [granite-3.0-3b-a800m-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_M.gguf) | Q3_K_M | 1.644 GB | very small, high quality loss |
+| [granite-3.0-3b-a800m-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q3_K_L.gguf) | Q3_K_L | 1.774 GB | small, substantial quality loss |
+| [granite-3.0-3b-a800m-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_0.gguf) | Q4_0 | 1.926 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-3b-a800m-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_K_S.gguf) | Q4_K_S | 1.942 GB | small, greater quality loss |
+| [granite-3.0-3b-a800m-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q4_K_M.gguf) | Q4_K_M | 2.059 GB | medium, balanced quality - recommended |
+| [granite-3.0-3b-a800m-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q5_0.gguf) | Q5_0 | 2.338 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-3b-a800m-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q5_K_S.gguf) | Q5_K_S | 2.338 GB | large, low quality loss - recommended |
+| [granite-3.0-3b-a800m-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q5_K_M.gguf) | Q5_K_M | 2.407 GB | large, very low quality loss - recommended |
+| [granite-3.0-3b-a800m-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-Q6_K.gguf) | Q6_K | 2.776 GB | very large, extremely low quality loss |
+| [granite-3.0-3b-a800m-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-3b-a800m-instruct-GGUF/blob/main/granite-3.0-3b-a800m-instruct-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-instruct-GGUF --include "granite-3.0-3b-a800m-instruct-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-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6eea4068cb76f0cdb9116305af0c566fc8c7dfb03c31a788e299378873f24e
+size 1266139968

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc46c81a1cd618b0cdc5c7c391a7771b990b6b39f3085a59da123594f011f38
+size 1773978880

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9dbca218b6f1700857dae53fea337250842c3c95f1654b296784e8af5e98e50
+size 1643627776

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851c4d705325b4604818cffa423134f280fef358e4e14fb84fe5ad5ba1921237
+size 1488504064

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4bc4951ea9639218a725feee22efe6f2ba6f38a34a5b754b03787aaf3df7d2
+size 1926350688

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9741db50f55c936ce1bc37e0133e1d35aa88022a8e612a24df2eca95f3c25fc
+size 2059356000

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07132931d1c01213001301c1cc22b2177937ce1bb985183dc55431cfbf6efdbe
+size 1942472544

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4b99d5f68efe4111d624e9e4804a029d34fe405baf9dcd17c4dcc59bf72b38
+size 2338441632

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8dac745775e5eeeba291e80f2cc6f1b25af29db5536b89d2d8c7ead140b922
+size 2406959520

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998fdbc063badd2a7c180bcd4a07848bc5e68a236800fb904fca53d1bb6d3aaf
+size 2338441632

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71910df896d8afa2dc84b2b68f22d8ccf0d51d0f81f7ace2e17e67de4855c58b
+size 2776288288

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb6eba1bfcbad9a4e40f3478e28c6e4d6502a99efa672c450317897c5aeb7b5
+size 3593000096