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-128k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-instruct-128k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,144 @@
+---
+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-8b-code-instruct-128k
+model-index:
+- name: granite-8B-Code-instruct-128k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis (Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 62.2
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 51.4
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 38.9
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 38.3
+      name: pass@1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoQA (Python@16K)
+      type: repoqa
+    metrics:
+    - type: pass@1 (thresh=0.5)
+      value: 73.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 37.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 73.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 62.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 63.0
+      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-8b-code-instruct-128k - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-8b-code-instruct-128k](https://huggingface.co/ibm-granite/granite-8b-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).
+
+## Prompt template
+
+```
+System:
+{system_prompt}
+
+Question:
+{prompt}
+
+Answer:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-8b-code-instruct-128k-Q2_K.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q2_K.gguf) | Q2_K | 2.852 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-8b-code-instruct-128k-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q3_K_S.gguf) | Q3_K_S | 3.304 GB | very small, high quality loss |
+| [granite-8b-code-instruct-128k-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q3_K_M.gguf) | Q3_K_M | 3.674 GB | very small, high quality loss |
+| [granite-8b-code-instruct-128k-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q3_K_L.gguf) | Q3_K_L | 3.993 GB | small, substantial quality loss |
+| [granite-8b-code-instruct-128k-Q4_0.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q4_0.gguf) | Q4_0 | 4.276 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-8b-code-instruct-128k-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q4_K_S.gguf) | Q4_K_S | 4.305 GB | small, greater quality loss |
+| [granite-8b-code-instruct-128k-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q4_K_M.gguf) | Q4_K_M | 4.548 GB | medium, balanced quality - recommended |
+| [granite-8b-code-instruct-128k-Q5_0.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q5_0.gguf) | Q5_0 | 5.190 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-8b-code-instruct-128k-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q5_K_S.gguf) | Q5_K_S | 5.190 GB | large, low quality loss - recommended |
+| [granite-8b-code-instruct-128k-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q5_K_M.gguf) | Q5_K_M | 5.330 GB | large, very low quality loss - recommended |
+| [granite-8b-code-instruct-128k-Q6_K.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-Q6_K.gguf) | Q6_K | 6.161 GB | very large, extremely low quality loss |
+| [granite-8b-code-instruct-128k-Q8_0.gguf](https://huggingface.co/tensorblock/granite-8b-code-instruct-128k-GGUF/tree/main/granite-8b-code-instruct-128k-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-128k-GGUF --include "granite-8b-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-8b-code-instruct-128k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-8b-code-instruct-128k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e2417c0c8e2e515aed0ef0ce0a5cf21b6fd81c023d17c993ab6c59e4cf8061
+size 3062071168

granite-8b-code-instruct-128k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1382114244aa9dea149436cae98eeb91e707475dc364f61f519b22d7faa2f76b
+size 4287725440

granite-8b-code-instruct-128k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b8d8cdba311586998eadbfb0e1dd924d69d63dbfc27994360b4031d235379c
+size 3944841088

granite-8b-code-instruct-128k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f598a0fbf47c7c45a3aa05b113d77ad0f5b3a68642c6135c5e987ec9e5023427
+size 3548086144

granite-8b-code-instruct-128k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d51547840cc28a6d8a5c261769bff2767d6c515de5d1c1e2ebfd64915057cb
+size 4590894976

granite-8b-code-instruct-128k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04680b9c3770f0e76b3399613cb16054211d92d9d43ce395fc94919cfcf638b1
+size 4882857856

granite-8b-code-instruct-128k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a759447e056556dbe0ff721194677b2d91db8289f015f54724964af56ed51cc4
+size 4622352256

granite-8b-code-instruct-128k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6cea2eec37b73a126536989b3d1f11e2c8c25af6bc6ea6ff3e971e646511748
+size 5572362112

granite-8b-code-instruct-128k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c4493d6f184275e654ebdd2ea5a0e8d93dcd2af5f149cd79270eb5d8c381d0
+size 5722767232

granite-8b-code-instruct-128k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979e66fd59ebec2f8d86dc7c7a08ff636b9608b7169c469c925ca2358e3b0cda
+size 5572362112

granite-8b-code-instruct-128k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109497efa8560c94aaf68fffb599918258e4b246ffba97020a91719f0c644897
+size 6615170944

granite-8b-code-instruct-128k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e301355a06a653fd7b27508abfe91abfce707c479bda0b7b21c345bafc0f370
+size 8565522304