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-20b-code-base-r1.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-code-base-r1.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,151 @@
+---
+pipeline_tag: text-generation
+inference: true
+license: apache-2.0
+datasets:
+- codeparrot/github-code-clean
+- bigcode/starcoderdata
+- open-web-math/open-web-math
+- math-ai/StackMathQA
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+- TensorBlock
+- GGUF
+base_model: ibm-granite/granite-20b-code-base-r1.1
+model-index:
+- name: granite-20b-code-base-r1.1
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 48.2
+      name: pass@1
+    - type: pass@1
+      value: 56.1
+      name: pass@1
+    - type: pass@1
+      value: 59.8
+      name: pass@1
+    - type: pass@1
+      value: 33.5
+      name: pass@1
+    - type: pass@1
+      value: 50.6
+      name: pass@1
+    - type: pass@1
+      value: 40.9
+      name: pass@1
+    - type: pass@1
+      value: 28.7
+      name: pass@1
+    - type: pass@1
+      value: 24.4
+      name: pass@1
+    - type: pass@1
+      value: 43.3
+      name: pass@1
+    - type: pass@1
+      value: 13.8
+      name: pass@1
+    - type: pass@1
+      value: 29.9
+      name: pass@1
+    - type: pass@1
+      value: 18.3
+      name: pass@1
+    - type: pass@1
+      value: 22.0
+      name: pass@1
+    - type: pass@1
+      value: 24.4
+      name: pass@1
+    - type: pass@1
+      value: 32.3
+      name: pass@1
+    - type: pass@1
+      value: 28.0
+      name: pass@1
+    - type: pass@1
+      value: 30.5
+      name: pass@1
+    - type: pass@1
+      value: 13.4
+      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-20b-code-base-r1.1 - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-20b-code-base-r1.1](https://huggingface.co/ibm-granite/granite-20b-code-base-r1.1).
+
+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-20b-code-base-r1.1-Q2_K.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q2_K.gguf) | Q2_K | 7.929 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-20b-code-base-r1.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q3_K_S.gguf) | Q3_K_S | 8.935 GB | very small, high quality loss |
+| [granite-20b-code-base-r1.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q3_K_M.gguf) | Q3_K_M | 10.566 GB | very small, high quality loss |
+| [granite-20b-code-base-r1.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q3_K_L.gguf) | Q3_K_L | 11.737 GB | small, substantial quality loss |
+| [granite-20b-code-base-r1.1-Q4_0.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q4_0.gguf) | Q4_0 | 11.552 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-20b-code-base-r1.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q4_K_S.gguf) | Q4_K_S | 11.666 GB | small, greater quality loss |
+| [granite-20b-code-base-r1.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q4_K_M.gguf) | Q4_K_M | 12.820 GB | medium, balanced quality - recommended |
+| [granite-20b-code-base-r1.1-Q5_0.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q5_0.gguf) | Q5_0 | 14.016 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-20b-code-base-r1.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q5_K_S.gguf) | Q5_K_S | 14.016 GB | large, low quality loss - recommended |
+| [granite-20b-code-base-r1.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q5_K_M.gguf) | Q5_K_M | 14.809 GB | large, very low quality loss - recommended |
+| [granite-20b-code-base-r1.1-Q6_K.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q6_K.gguf) | Q6_K | 16.634 GB | very large, extremely low quality loss |
+| [granite-20b-code-base-r1.1-Q8_0.gguf](https://huggingface.co/tensorblock/granite-20b-code-base-r1.1-GGUF/blob/main/granite-20b-code-base-r1.1-Q8_0.gguf) | Q8_0 | 21.481 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-20b-code-base-r1.1-GGUF --include "granite-20b-code-base-r1.1-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-20b-code-base-r1.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-20b-code-base-r1.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f650ef8dc41998d0f04c24b03d0ee9dea080e29ec091f494050dfb9c3951d6a0
+size 7929485152

granite-20b-code-base-r1.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffcc22b1940fc1dc36cc2f3f4d5aec22e95ef46b18ac502478928a34998206a
+size 11736504160

granite-20b-code-base-r1.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8241339d85114568a408172d7974b5925d7adf0c7bb1ce71711d3de85cfe9f
+size 10566293344

granite-20b-code-base-r1.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf93b5f1efd54a2fb874f69438c1d67e5547965ac2f15443ebbbe04baf12e613
+size 8934594400

granite-20b-code-base-r1.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c9af833412c56a736855cd2f766ae4b9a56e59443445915195769d368eb4bc
+size 11552479072

granite-20b-code-base-r1.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3422315ce96a8b6befe4ed4cd7ab47929a94814efb0a7da3c72ed4de69e0dbe0
+size 12820207456

granite-20b-code-base-r1.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503b654222911edd2fd945f9293d543d52dfc96a89afaf412d1788080a958694
+size 11665725280

granite-20b-code-base-r1.1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316e06e9d07bfee9204f590ea7601b06b90dfc20647d316cac063c84370984ed
+size 14016370528

granite-20b-code-base-r1.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b42d2e1c6c8a135e7c4ad353c105c8d803c06fa2f5dc8581edef28058715e1
+size 14809339744

granite-20b-code-base-r1.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c82aa05b4f4fca6ea5bd99da0105e6fc284dd0f8d199a06ab378990e914e193
+size 14016370528

granite-20b-code-base-r1.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfa7106cb2154fe0688360a584353424c1c12e314fbada7cb981e63389156ef
+size 16634255200

granite-20b-code-base-r1.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feeee9050449579bcde74d1189201b8045813550e6723258d9ae4f7f0c600f5d
+size 21481183072