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-base-8k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-34b-code-base-8k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,163 @@
+---
+pipeline_tag: text-generation
+inference: true
+license: apache-2.0
+datasets:
+- codeparrot/github-code-clean
+- bigcode/starcoderdata
+- open-web-math/open-web-math
+- math-ai/StackMathQA
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+- TensorBlock
+- GGUF
+base_model: ibm-granite/granite-34b-code-base-8k
+model-index:
+- name: granite-34b-code-base-8k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MBPP
+      type: mbpp
+    metrics:
+    - type: pass@1
+      value: 47.2
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: MBPP+
+      type: evalplus/mbppplus
+    metrics:
+    - type: pass@1
+      value: 53.1
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 48.2
+      name: pass@1
+    - type: pass@1
+      value: 54.9
+      name: pass@1
+    - type: pass@1
+      value: 61.6
+      name: pass@1
+    - type: pass@1
+      value: 40.2
+      name: pass@1
+    - type: pass@1
+      value: 50.0
+      name: pass@1
+    - type: pass@1
+      value: 39.6
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 26.2
+      name: pass@1
+    - type: pass@1
+      value: 47.0
+      name: pass@1
+    - type: pass@1
+      value: 26.8
+      name: pass@1
+    - type: pass@1
+      value: 36.6
+      name: pass@1
+    - type: pass@1
+      value: 25.0
+      name: pass@1
+    - type: pass@1
+      value: 20.1
+      name: pass@1
+    - type: pass@1
+      value: 30.5
+      name: pass@1
+    - type: pass@1
+      value: 40.9
+      name: pass@1
+    - type: pass@1
+      value: 34.1
+      name: pass@1
+    - type: pass@1
+      value: 39.0
+      name: pass@1
+    - type: pass@1
+      value: 12.2
+      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-base-8k - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-34b-code-base-8k](https://huggingface.co/ibm-granite/granite-34b-code-base-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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-34b-code-base-8k-Q2_K.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q2_K.gguf) | Q2_K | 12.207 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-34b-code-base-8k-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q3_K_S.gguf) | Q3_K_S | 13.791 GB | very small, high quality loss |
+| [granite-34b-code-base-8k-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q3_K_M.gguf) | Q3_K_M | 16.361 GB | very small, high quality loss |
+| [granite-34b-code-base-8k-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q3_K_L.gguf) | Q3_K_L | 18.207 GB | small, substantial quality loss |
+| [granite-34b-code-base-8k-Q4_0.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q4_0.gguf) | Q4_0 | 17.917 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-34b-code-base-8k-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q4_K_S.gguf) | Q4_K_S | 18.110 GB | small, greater quality loss |
+| [granite-34b-code-base-8k-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q4_K_M.gguf) | Q4_K_M | 19.915 GB | medium, balanced quality - recommended |
+| [granite-34b-code-base-8k-Q5_0.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q5_0.gguf) | Q5_0 | 21.800 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-34b-code-base-8k-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q5_K_S.gguf) | Q5_K_S | 21.800 GB | large, low quality loss - recommended |
+| [granite-34b-code-base-8k-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q5_K_M.gguf) | Q5_K_M | 23.050 GB | large, very low quality loss - recommended |
+| [granite-34b-code-base-8k-Q6_K.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-8k-Q6_K.gguf) | Q6_K | 25.926 GB | very large, extremely low quality loss |
+| [granite-34b-code-base-8k-Q8_0.gguf](https://huggingface.co/tensorblock/granite-34b-code-base-8k-GGUF/tree/main/granite-34b-code-base-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-base-8k-GGUF --include "granite-34b-code-base-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-base-8k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b716f14e667a4a5c7af23a227de7b8489877ff97586c3bb825a37b574a0d2924
+size 13107021280

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666086c36d2e4db351ff2b8091ec87a2043053ef718b0b61127b724e3f443a73
+size 19549668832

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59536115c52f3fd162e37d2310c090dfa5517905fdd3c0c18da6c4c365890fb8
+size 17567860192

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3035b0207218547d8a22a7083ef67490bda5820ddf80966f4e52ba1d0e57b0
+size 14807975392

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b841cc79f4de50dae0da9923f11c1da25d251586d85cb177ac42aecf2e9a196e
+size 19238241760

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eecb174f654015b6b5eec5dbb5b0b857300fc4eaa3320002f2821064aae47c8
+size 21383628256

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ffd15c170db732e93e264954d8c03a09734a91a9b0837b85ee849a63f7c006
+size 19445859808

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab72164b6617dd9252f5a0358d2091dd45c999a77445c25249e3a0d41f2b5f4
+size 23407904224

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b9fc16ac622ac8ab2529b91c32006e8d618ab7d5f25b1039efcd6356437f20
+size 24749852128

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971472149f9dd3265501a0dd845d9ca2650087457644261fc73eaefd7b28b30f
+size 23407904224

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a405c23ee5b877855415969d610ee1cc2e9c5bf3344b76a355738f7f0e8c82
+size 27838170592

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2741b2ee9e0de5c320f73ebf4a1e38b9be096fe00af8254b3779089eb719ce6a
+size 35990029792