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-2k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-instruct-2k-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-3b-code-instruct-2k
+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-3b-code-instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 51.2
+      name: pass@1
+    - type: pass@1
+      value: 43.9
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 31.7
+      name: pass@1
+    - type: pass@1
+      value: 40.2
+      name: pass@1
+    - type: pass@1
+      value: 29.3
+      name: pass@1
+    - type: pass@1
+      value: 39.6
+      name: pass@1
+    - type: pass@1
+      value: 26.8
+      name: pass@1
+    - type: pass@1
+      value: 39.0
+      name: pass@1
+    - type: pass@1
+      value: 14.0
+      name: pass@1
+    - type: pass@1
+      value: 23.8
+      name: pass@1
+    - type: pass@1
+      value: 12.8
+      name: pass@1
+    - type: pass@1
+      value: 26.8
+      name: pass@1
+    - type: pass@1
+      value: 28.0
+      name: pass@1
+    - type: pass@1
+      value: 33.5
+      name: pass@1
+    - type: pass@1
+      value: 27.4
+      name: pass@1
+    - type: pass@1
+      value: 31.7
+      name: pass@1
+    - type: pass@1
+      value: 16.5
+      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-3b-code-instruct-2k - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3b-code-instruct-2k](https://huggingface.co/ibm-granite/granite-3b-code-instruct-2k).
+
+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-3b-code-instruct-2k-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q2_K.gguf) | Q2_K | 1.247 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3b-code-instruct-2k-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q3_K_S.gguf) | Q3_K_S | 1.445 GB | very small, high quality loss |
+| [granite-3b-code-instruct-2k-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q3_K_M.gguf) | Q3_K_M | 1.608 GB | very small, high quality loss |
+| [granite-3b-code-instruct-2k-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q3_K_L.gguf) | Q3_K_L | 1.747 GB | small, substantial quality loss |
+| [granite-3b-code-instruct-2k-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q4_0.gguf) | Q4_0 | 1.860 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3b-code-instruct-2k-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q4_K_S.gguf) | Q4_K_S | 1.875 GB | small, greater quality loss |
+| [granite-3b-code-instruct-2k-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q4_K_M.gguf) | Q4_K_M | 1.986 GB | medium, balanced quality - recommended |
+| [granite-3b-code-instruct-2k-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q5_0.gguf) | Q5_0 | 2.251 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3b-code-instruct-2k-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q5_K_S.gguf) | Q5_K_S | 2.251 GB | large, low quality loss - recommended |
+| [granite-3b-code-instruct-2k-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q5_K_M.gguf) | Q5_K_M | 2.316 GB | large, very low quality loss - recommended |
+| [granite-3b-code-instruct-2k-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-Q6_K.gguf) | Q6_K | 2.666 GB | very large, extremely low quality loss |
+| [granite-3b-code-instruct-2k-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3b-code-instruct-2k-GGUF/tree/main/granite-3b-code-instruct-2k-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-2k-GGUF --include "granite-3b-code-instruct-2k-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-2k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3b-code-instruct-2k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520aa8511266506903e17b519ed2c5692e9ce22b3b32d2cb645889eefee5d8d0
+size 1338694240

granite-3b-code-instruct-2k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07b8ed370ae76cecb423b19e97ab03bf0864c17aa1c7e232d1448b35a4542f0
+size 1876089440

granite-3b-code-instruct-2k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef9b621f768fda8acb6cd08f3e5439d2943c2df9553fb364a15c9e4e24e3993
+size 1726995040

granite-3b-code-instruct-2k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dff17a97cb09d4a37bd3f32710fb67ced6645e4ecaf5abea81d358335882a6
+size 1551686240

granite-3b-code-instruct-2k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807a21d625884a31a897ab5781f3875972137922730658e08d3a959ce8f32b4e
+size 1997331040

granite-3b-code-instruct-2k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b9df998dddc8c3a62935445023dd3ce8c6fc0445596c2a11bfbcb6bd9af9a4
+size 2132499040

granite-3b-code-instruct-2k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a896a8986c6b479c129ee15691a74446c606ed64ae94f5a967a548167b6013f6
+size 2013715040

granite-3b-code-instruct-2k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5025cdf89b10e544b4e45860ee6395be39477b6f567602695eb884a52c9b9892
+size 2416761440

granite-3b-code-instruct-2k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d9170372cd6094ad931106e009e7cc6229f9cce7ceaa7c859f4d0292d1944a
+size 2486393440

granite-3b-code-instruct-2k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ffef9d61887c8175659df73526b5c4d364841320b1a1ac7d723212a4a3ef2a
+size 2416761440

granite-3b-code-instruct-2k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161037c71b443443ea5472b8c4c740b27358abec4c6bb4790d3523bec08b5ba7
+size 2862406240

granite-3b-code-instruct-2k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b855882642be8afee1e46d31a6a2df1a2e2334e2600beb777e6cebfa7eac1dd
+size 3705526880