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-3b-code-instruct-128k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-128k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,150 @@
+---
+pipeline_tag: text-generation
+inference: false
+license: apache-2.0
+datasets:
+- bigcode/commitpackft
+- TIGER-Lab/MathInstruct
+- meta-math/MetaMathQA
+- glaiveai/glaive-code-assistant-v3
+- glaive-function-calling-v2
+- bugdaryan/sql-create-context-instruction
+- garage-bAInd/Open-Platypus
+- nvidia/HelpSteer
+- bigcode/self-oss-instruct-sc2-exec-filter-50k
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+- TensorBlock
+- GGUF
+base_model: ibm-granite/granite-3b-code-instruct-128k
+model-index:
+- name: granite-3b-code-instruct-128k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis (Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 53.7
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 41.4
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 25.1
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 26.2
+      name: pass@1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoQA (Python@16K)
+      type: repoqa
+    metrics:
+    - type: pass@1 (thresh=0.5)
+      value: 48.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 36.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 38.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 39.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 29.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+---
+
+<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-3b-code-instruct-128k - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3b-code-instruct-128k](https://huggingface.co/ibm-granite/granite-3b-code-instruct-128k).
+
+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
+
+```
+System:
+{system_prompt}
+
+Question:
+{prompt}
+
+Answer:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-3b-code-instruct-128k-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q2_K.gguf) | Q2_K | 1.247 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3b-code-instruct-128k-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q3_K_S.gguf) | Q3_K_S | 1.445 GB | very small, high quality loss |
+| [granite-3b-code-instruct-128k-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q3_K_M.gguf) | Q3_K_M | 1.608 GB | very small, high quality loss |
+| [granite-3b-code-instruct-128k-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q3_K_L.gguf) | Q3_K_L | 1.747 GB | small, substantial quality loss |
+| [granite-3b-code-instruct-128k-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q4_0.gguf) | Q4_0 | 1.860 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3b-code-instruct-128k-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q4_K_S.gguf) | Q4_K_S | 1.875 GB | small, greater quality loss |
+| [granite-3b-code-instruct-128k-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q4_K_M.gguf) | Q4_K_M | 1.986 GB | medium, balanced quality - recommended |
+| [granite-3b-code-instruct-128k-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q5_0.gguf) | Q5_0 | 2.251 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3b-code-instruct-128k-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q5_K_S.gguf) | Q5_K_S | 2.251 GB | large, low quality loss - recommended |
+| [granite-3b-code-instruct-128k-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q5_K_M.gguf) | Q5_K_M | 2.316 GB | large, very low quality loss - recommended |
+| [granite-3b-code-instruct-128k-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q6_K.gguf) | Q6_K | 2.666 GB | very large, extremely low quality loss |
+| [granite-3b-code-instruct-128k-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-128k-GGUF/blob/main/granite-3b-code-instruct-128k-Q8_0.gguf) | Q8_0 | 3.451 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-3b-code-instruct-128k-GGUF --include "granite-3b-code-instruct-128k-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-3b-code-instruct-128k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3b-code-instruct-128k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d0b78d721bf748a391e75e267f1219ec82dfffa30476ad0fad39d4f6db6881
+size 1338694016

granite-3b-code-instruct-128k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6289d36e8da7db2a05d4ce8f506f38221d80ff437748061de7b3f827f7bc2b6d
+size 1876089216

granite-3b-code-instruct-128k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be1af1e71e7810b9a5dfe054e163e8e6cb9223d8b235ec7a34a77128807f115
+size 1726994816

granite-3b-code-instruct-128k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3505f7058837518913c9ebed44d7fab004a8af744b82e677a9910315aa8aca44
+size 1551686016

granite-3b-code-instruct-128k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259e525afc718ba49b87472e666ff0673cf8dd90f4f1c59a8be640d4e43ad87b
+size 1997330816

granite-3b-code-instruct-128k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27e1f8798d9ab1f1c2af435f71844990c8a8e889459539ca57c4882b4729fca
+size 2132498816

granite-3b-code-instruct-128k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3f8429a028d507463e28f0f1d3b212089687290f3e6a45159fd4e939636184
+size 2013714816

granite-3b-code-instruct-128k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e557c5f95057f548e22ce32fa474f964052d117b6878331e5f4266bb186cde
+size 2416761216

granite-3b-code-instruct-128k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad97024600c7be3e13ad360161b2fe806b6e45d00c6db34fb1b03d01a84565a
+size 2486393216

granite-3b-code-instruct-128k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9a15f2ceb81334f1a0654d5d2a335a1066a7e765bf3938aa21eedc2ec07b6c
+size 2416761216

granite-3b-code-instruct-128k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ff4b25dcb2e0799dc2eacfe09f97a7087edc36e804366ade18ad88c85a8afc
+size 2862406016

granite-3b-code-instruct-128k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e937e8d8054ff5383ac8b410bbf29ee6bf76bde543848076a8aa9ee274868b8b
+size 3705526656