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-34b-code-instruct-8k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-instruct-8k-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-34b-code-instruct-8k
+inference: true
+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-34b-code-instruct-8k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 62.2
+      name: pass@1
+    - type: pass@1
+      value: 56.7
+      name: pass@1
+    - type: pass@1
+      value: 62.8
+      name: pass@1
+    - type: pass@1
+      value: 47.6
+      name: pass@1
+    - type: pass@1
+      value: 57.9
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 53.0
+      name: pass@1
+    - type: pass@1
+      value: 45.1
+      name: pass@1
+    - type: pass@1
+      value: 50.6
+      name: pass@1
+    - type: pass@1
+      value: 36.0
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 23.8
+      name: pass@1
+    - type: pass@1
+      value: 54.9
+      name: pass@1
+    - type: pass@1
+      value: 47.6
+      name: pass@1
+    - type: pass@1
+      value: 55.5
+      name: pass@1
+    - type: pass@1
+      value: 51.2
+      name: pass@1
+    - type: pass@1
+      value: 47.0
+      name: pass@1
+    - type: pass@1
+      value: 45.1
+      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-34b-code-instruct-8k - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-34b-code-instruct-8k](https://huggingface.co/ibm-granite/granite-34b-code-instruct-8k).
+
+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-34b-code-instruct-8k-Q2_K.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q2_K.gguf) | Q2_K | 12.207 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-34b-code-instruct-8k-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q3_K_S.gguf) | Q3_K_S | 13.791 GB | very small, high quality loss |
+| [granite-34b-code-instruct-8k-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q3_K_M.gguf) | Q3_K_M | 16.361 GB | very small, high quality loss |
+| [granite-34b-code-instruct-8k-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q3_K_L.gguf) | Q3_K_L | 18.207 GB | small, substantial quality loss |
+| [granite-34b-code-instruct-8k-Q4_0.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q4_0.gguf) | Q4_0 | 17.917 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-34b-code-instruct-8k-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q4_K_S.gguf) | Q4_K_S | 18.110 GB | small, greater quality loss |
+| [granite-34b-code-instruct-8k-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q4_K_M.gguf) | Q4_K_M | 19.915 GB | medium, balanced quality - recommended |
+| [granite-34b-code-instruct-8k-Q5_0.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q5_0.gguf) | Q5_0 | 21.800 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-34b-code-instruct-8k-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q5_K_S.gguf) | Q5_K_S | 21.800 GB | large, low quality loss - recommended |
+| [granite-34b-code-instruct-8k-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q5_K_M.gguf) | Q5_K_M | 23.050 GB | large, very low quality loss - recommended |
+| [granite-34b-code-instruct-8k-Q6_K.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q6_K.gguf) | Q6_K | 25.926 GB | very large, extremely low quality loss |
+| [granite-34b-code-instruct-8k-Q8_0.gguf](https://huggingface.co/tensorblock/granite-34b-code-instruct-8k-GGUF/tree/main/granite-34b-code-instruct-8k-Q8_0.gguf) | Q8_0 | 33.518 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-34b-code-instruct-8k-GGUF --include "granite-34b-code-instruct-8k-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-34b-code-instruct-8k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-34b-code-instruct-8k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e990e259feae3d5c02341b691163ca7584dba1f16d0cef109bb641676050c5
+size 13107022144

granite-34b-code-instruct-8k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bb91dd64da7cf04163f39da9bde159b698d43721f54d9d34215c2ccb9386ac
+size 19549669696

granite-34b-code-instruct-8k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466579373e98ec72dc0f6543eea71509a1e5de1b5e189c46b4d8dbc34f816882
+size 17567861056

granite-34b-code-instruct-8k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04a0744c7ffca0cd710469238db80e49bcc7e02ecb4a23b88147bd213dc4062
+size 14807976256

granite-34b-code-instruct-8k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fddde839433f20a0087c0a6072693fb55151403b9a0c71279f65a16bddcb9a
+size 19238242624

granite-34b-code-instruct-8k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982eff4a94083b558da1f21814841bc262e5c8dffc5bbc7d164441002961ab9f
+size 21383629120

granite-34b-code-instruct-8k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac6ef8f4fc9fa18ef19ad14d17adecfd1c229af45c2dd061d645fb2468bb424
+size 19445860672

granite-34b-code-instruct-8k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7735b0f47fcf3abab6cd03adf9514c3a66c973cd52d69ccf9fb02ab6170e7995
+size 23407905088

granite-34b-code-instruct-8k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe80956278b94a2369ab6e3d7ce9d0b03fcc27af7552195fef689b6334b167c5
+size 24749852992

granite-34b-code-instruct-8k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cd2307c0e3e1d2e2656264de1ca7276afa1a92c4e49e16103618c1834b0800
+size 23407905088

granite-34b-code-instruct-8k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534c9e2d41729dc85c277fdbacb4ee19973afa5f0bdf34a42cbd479e76d5956f
+size 27838171456

granite-34b-code-instruct-8k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbb05a4ec263d51670bbf5c88fab26cdc942a7b8d2ecd2b783fe726bf0bd43a
+size 35990030656