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-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-1b-a400m-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-3.0-1b-a400m-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: 32.39
+      name: pass@1
+    - type: pass@1
+      value: 6.17
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: AGI-Eval
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 20.35
+      name: pass@1
+    - type: pass@1
+      value: 32
+      name: pass@1
+    - type: pass@1
+      value: 12.21
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: OBQA
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 38.4
+      name: pass@1
+    - type: pass@1
+      value: 47.55
+      name: pass@1
+    - type: pass@1
+      value: 65.59
+      name: pass@1
+    - type: pass@1
+      value: 61.17
+      name: pass@1
+    - type: pass@1
+      value: 49.11
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 70.12
+      name: pass@1
+    - type: pass@1
+      value: 1.27
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 41.21
+      name: pass@1
+    - type: pass@1
+      value: 23.07
+      name: pass@1
+    - type: pass@1
+      value: 31.77
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis
+      type: code
+    metrics:
+    - type: pass@1
+      value: 30.18
+      name: pass@1
+    - type: pass@1
+      value: 26.22
+      name: pass@1
+    - type: pass@1
+      value: 21.95
+      name: pass@1
+    - type: pass@1
+      value: 15.4
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 26.31
+      name: pass@1
+    - type: pass@1
+      value: 10.88
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: PAWS-X (7 langs)
+      type: multilingual
+    metrics:
+    - type: pass@1
+      value: 45.84
+      name: pass@1
+    - type: pass@1
+      value: 11.8
+      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-instruct - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-1b-a400m-instruct](https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-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-3.0-1b-a400m-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q2_K.gguf) | Q2_K | 0.512 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-1b-a400m-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q3_K_S.gguf) | Q3_K_S | 0.598 GB | very small, high quality loss |
+| [granite-3.0-1b-a400m-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q3_K_M.gguf) | Q3_K_M | 0.659 GB | very small, high quality loss |
+| [granite-3.0-1b-a400m-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q3_K_L.gguf) | Q3_K_L | 0.711 GB | small, substantial quality loss |
+| [granite-3.0-1b-a400m-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q4_0.gguf) | Q4_0 | 0.768 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-1b-a400m-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q4_K_S.gguf) | Q4_K_S | 0.775 GB | small, greater quality loss |
+| [granite-3.0-1b-a400m-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q4_K_M.gguf) | Q4_K_M | 0.822 GB | medium, balanced quality - recommended |
+| [granite-3.0-1b-a400m-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q5_0.gguf) | Q5_0 | 0.929 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-1b-a400m-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q5_K_S.gguf) | Q5_K_S | 0.929 GB | large, low quality loss - recommended |
+| [granite-3.0-1b-a400m-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q5_K_M.gguf) | Q5_K_M | 0.956 GB | large, very low quality loss - recommended |
+| [granite-3.0-1b-a400m-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q6_K.gguf) | Q6_K | 1.099 GB | very large, extremely low quality loss |
+| [granite-3.0-1b-a400m-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-1b-a400m-instruct-GGUF/blob/main/granite-3.0-1b-a400m-instruct-Q8_0.gguf) | Q8_0 | 1.422 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-instruct-GGUF --include "granite-3.0-1b-a400m-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-3.0-1b-a400m-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab42f5f418808ee640a7a8db09c8756b8b3c1942cf27881dc0019f9b040760fe
+size 512236576

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9523a85c6020a621ba09242ba20bce6ea5266233198ef1c031d392e212c1bde
+size 711400480

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb21263c3b4121aaedb4da26b3b1e8c00e6f8b271142644c882c8bd4fb51dad
+size 658578464

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46740870d24328fdbb56a778d2a49e913633971760c9ddced1dac3b281d9f661
+size 597859360

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f296e7e0bbd42b20deae8e3ce82f3b67dbe2375615c03d7a074788c37f7f8586
+size 768318496

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6887e84bef32fa11bac90e5f060ee35d4e28d061f2c1196aef5237e770b27ce
+size 821845024

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57662e3fa06d16994d1b7171d9493d0bf44180d66f74f740c6c6bd928bf2b954
+size 774872096

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f06ff4ccbce42bc617975f9f6972facb6a5923eef57057d6710f948c45b5aa9
+size 928750624

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eee5f59a3aee7003e04d331765251067d75b42ff01fe545326cb304afcc7c13
+size 956324896

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dceb619c0c2e185e76bba7aabce6eb7d5b798621cf8f77b5f0938e15f854de19
+size 928750624

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a955e00ca8ebc1e2c1a899dbf88b7862c1dd7642c7e8bdb599295eacf99c724f
+size 1099209760

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bb507b0745871c760978541b3809f27739e044d513c0af0349b9d86cdfb41b
+size 1422237440