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-8b-code-instruct-4k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-4k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,155 @@
+---
+pipeline_tag: text-generation
+base_model: ibm-granite/granite-8b-code-instruct-4k
+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
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+- TensorBlock
+- GGUF
+model-index:
+- name: granite-8b-code-instruct-4k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 57.9
+      name: pass@1
+    - type: pass@1
+      value: 52.4
+      name: pass@1
+    - type: pass@1
+      value: 58.5
+      name: pass@1
+    - type: pass@1
+      value: 43.3
+      name: pass@1
+    - type: pass@1
+      value: 48.2
+      name: pass@1
+    - type: pass@1
+      value: 37.2
+      name: pass@1
+    - type: pass@1
+      value: 53.0
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 52.4
+      name: pass@1
+    - type: pass@1
+      value: 36.6
+      name: pass@1
+    - type: pass@1
+      value: 43.9
+      name: pass@1
+    - type: pass@1
+      value: 16.5
+      name: pass@1
+    - type: pass@1
+      value: 39.6
+      name: pass@1
+    - type: pass@1
+      value: 40.9
+      name: pass@1
+    - type: pass@1
+      value: 48.2
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 39.0
+      name: pass@1
+    - type: pass@1
+      value: 32.9
+      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-8b-code-instruct-4k - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-8b-code-instruct-4k](https://huggingface.co/ibm-granite/granite-8b-code-instruct-4k).
+
+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).
+
+## Prompt template
+
+```
+System:
+{system_prompt}
+
+Question:
+{prompt}
+
+Answer:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-8b-code-instruct-4k-Q2_K.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q2_K.gguf) | Q2_K | 2.852 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-8b-code-instruct-4k-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q3_K_S.gguf) | Q3_K_S | 3.304 GB | very small, high quality loss |
+| [granite-8b-code-instruct-4k-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q3_K_M.gguf) | Q3_K_M | 3.674 GB | very small, high quality loss |
+| [granite-8b-code-instruct-4k-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q3_K_L.gguf) | Q3_K_L | 3.993 GB | small, substantial quality loss |
+| [granite-8b-code-instruct-4k-Q4_0.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q4_0.gguf) | Q4_0 | 4.276 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-8b-code-instruct-4k-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q4_K_S.gguf) | Q4_K_S | 4.305 GB | small, greater quality loss |
+| [granite-8b-code-instruct-4k-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q4_K_M.gguf) | Q4_K_M | 4.548 GB | medium, balanced quality - recommended |
+| [granite-8b-code-instruct-4k-Q5_0.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q5_0.gguf) | Q5_0 | 5.190 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-8b-code-instruct-4k-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q5_K_S.gguf) | Q5_K_S | 5.190 GB | large, low quality loss - recommended |
+| [granite-8b-code-instruct-4k-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q5_K_M.gguf) | Q5_K_M | 5.330 GB | large, very low quality loss - recommended |
+| [granite-8b-code-instruct-4k-Q6_K.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q6_K.gguf) | Q6_K | 6.161 GB | very large, extremely low quality loss |
+| [granite-8b-code-instruct-4k-Q8_0.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-4k-GGUF/tree/main/granite-8b-code-instruct-4k-Q8_0.gguf) | Q8_0 | 7.977 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-8b-code-instruct-4k-GGUF --include "granite-8b-code-instruct-4k-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-8b-code-instruct-4k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-8b-code-instruct-4k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1fc6c2fc119ab6199e5cc0d2ad781f018047fd0df3c1275c14d7f592ccfe7f
+size 3062071392

granite-8b-code-instruct-4k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245dd62fa9576e82c7493b48ba3856284c1079e09dd5647da95d6728ae9fec3f
+size 4287725664

granite-8b-code-instruct-4k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4331befe0d884fde4f0385fc3e8c054c4c49153b139a9902aa2214c57923eb5
+size 3944841312

granite-8b-code-instruct-4k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4414330a9aa964d1a4a95bdda7746b6a4dd6cb6fc502e297e9bb36f04658e493
+size 3548086368

granite-8b-code-instruct-4k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf470ee44e2977d776c753b7f638143250bbe6d5763a2d3eeee8ba4284c526fe
+size 4590895200

granite-8b-code-instruct-4k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ccb90486a0e35ad907ce0c5444e78a02c822236100e51abad8178668f3c753
+size 4882858080

granite-8b-code-instruct-4k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ca4c3836f95c48ddf300bebc5dbb3fef79f857376e7881c99f3fc4f25f7b6b
+size 4622352480

granite-8b-code-instruct-4k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f7fbcdfe9c22d9c60c5eb77064a46cb06e7037bdce59e7024c98cd4de03fa3
+size 5572362336

granite-8b-code-instruct-4k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f866f08763648b265faccda389088524d3d0cdd24d1b2d6ab9d97dd97a988a2
+size 5722767456

granite-8b-code-instruct-4k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ad42b886f952e8a8e2d55563550690c75b48889b102af44bfd9638d20ffc17
+size 5572362336

granite-8b-code-instruct-4k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442f2adbf619c851b72f77377fff9ff7409aebf6308d82e504bea4feb7193dd8
+size 6615171168

granite-8b-code-instruct-4k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b790b05553c8991d376f67c168accaacd8cda28c2e01f7a93d89ff6fe22cbc2
+size 8565522528