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-3.0-1b-a400m-base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-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-3.0-1b-a400m-base
+model-index:
+- name: granite-3.0-1b-a400m-base
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MMLU
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 25.69
+      name: pass@1
+    - type: pass@1
+      value: 11.38
+      name: pass@1
+    - type: pass@1
+      value: 19.96
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: WinoGrande
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 62.43
+      name: pass@1
+    - type: pass@1
+      value: 39.0
+      name: pass@1
+    - type: pass@1
+      value: 35.76
+      name: pass@1
+    - type: pass@1
+      value: 75.35
+      name: pass@1
+    - type: pass@1
+      value: 64.92
+      name: pass@1
+    - type: pass@1
+      value: 39.49
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 65.44
+      name: pass@1
+    - type: pass@1
+      value: 17.78
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 38.14
+      name: pass@1
+    - type: pass@1
+      value: 24.41
+      name: pass@1
+    - type: pass@1
+      value: 29.84
+      name: pass@1
+    - type: pass@1
+      value: 33.99
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: code
+    metrics:
+    - type: pass@1
+      value: 21.95
+      name: pass@1
+    - type: pass@1
+      value: 23.2
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 19.26
+      name: pass@1
+    - type: pass@1
+      value: 8.96
+      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-3.0-1b-a400m-base - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-1b-a400m-base](https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-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-3.0-1b-a400m-base-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q2_K.gguf) | Q2_K | 0.529 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-1b-a400m-base-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q3_K_S.gguf) | Q3_K_S | 0.619 GB | very small, high quality loss |
+| [granite-3.0-1b-a400m-base-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q3_K_M.gguf) | Q3_K_M | 0.680 GB | very small, high quality loss |
+| [granite-3.0-1b-a400m-base-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q3_K_L.gguf) | Q3_K_L | 0.733 GB | small, substantial quality loss |
+| [granite-3.0-1b-a400m-base-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q4_0.gguf) | Q4_0 | 0.797 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-1b-a400m-base-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q4_K_S.gguf) | Q4_K_S | 0.803 GB | small, greater quality loss |
+| [granite-3.0-1b-a400m-base-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q4_K_M.gguf) | Q4_K_M | 0.850 GB | medium, balanced quality - recommended |
+| [granite-3.0-1b-a400m-base-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q5_0.gguf) | Q5_0 | 0.963 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-1b-a400m-base-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q5_K_S.gguf) | Q5_K_S | 0.963 GB | large, low quality loss - recommended |
+| [granite-3.0-1b-a400m-base-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q5_K_M.gguf) | Q5_K_M | 0.991 GB | large, very low quality loss - recommended |
+| [granite-3.0-1b-a400m-base-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q6_K.gguf) | Q6_K | 1.140 GB | very large, extremely low quality loss |
+| [granite-3.0-1b-a400m-base-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-base-GGUF/blob/main/granite-3.0-1b-a400m-base-Q8_0.gguf) | Q8_0 | 1.476 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-3.0-1b-a400m-base-GGUF --include "granite-3.0-1b-a400m-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-3.0-1b-a400m-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3.0-1b-a400m-base-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c5628cb57ae3d9a3a973d6682e2c95318a94cf77f37f1bdd48ef6febb8f3c2
+size 528747584

granite-3.0-1b-a400m-base-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153ec3f673c2918558e957a56ea4695886117aab7ecfecc33eaac5bbd8bd50c8
+size 733023296

granite-3.0-1b-a400m-base-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0e47a903d8de1e617f87947d4015dea20198e4baed3208bdcf8ce788d933b7
+size 680201280

granite-3.0-1b-a400m-base-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c535b3189a8a04637624e44427ef360e569648cdaf23301f9a112f52cb367e3
+size 619482176

granite-3.0-1b-a400m-base-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0586a77cc14d8fbdbddaed56d70786302b27f6efa0dac55fc623702bb3f87c
+size 796625984

granite-3.0-1b-a400m-base-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd568693ac72b441248210d63ed14e070644032ba6cd2786758888440cce38a1
+size 850152512

granite-3.0-1b-a400m-base-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b2fa8d17449846a9101168599a5cda556ab978e28f041e494ebce88174109a
+size 803179584

granite-3.0-1b-a400m-base-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f4415e01c1a9d5957a643631b99c981ed12fa8bf91750bc2e99102a79a7e3e
+size 963349568

granite-3.0-1b-a400m-base-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97db0bc59d600d13e72daab717300ec40fc1b9775126ac0a92554d2b0acb554a
+size 990923840

granite-3.0-1b-a400m-base-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af1df0308e3acfcd4a865bf7ef30881eca4b2fad3525178705ec7610ce6943a
+size 963349568

granite-3.0-1b-a400m-base-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5849a5e3d198e9569c9f94a091150cfc6d2e2652509e2cf51988154ce94c3e4f
+size 1140493376

granite-3.0-1b-a400m-base-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7f29187f8eb2c542062f276ecad84661578e81d1d073ce52adbf80fd0f2b97
+size 1475710016