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-3.0-8b-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.0-8b-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,197 @@
+---
+pipeline_tag: text-generation
+inference: false
+license: apache-2.0
+library_name: transformers
+tags:
+- language
+- granite-3.0
+- TensorBlock
+- GGUF
+base_model: ibm-granite/granite-3.0-8b-instruct
+model-index:
+- name: granite-3.0-2b-instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: IFEval
+      type: instruction-following
+    metrics:
+    - type: pass@1
+      value: 52.27
+      name: pass@1
+    - type: pass@1
+      value: 8.22
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: AGI-Eval
+      type: human-exams
+    metrics:
+    - type: pass@1
+      value: 40.52
+      name: pass@1
+    - type: pass@1
+      value: 65.82
+      name: pass@1
+    - type: pass@1
+      value: 34.45
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: OBQA
+      type: commonsense
+    metrics:
+    - type: pass@1
+      value: 46.6
+      name: pass@1
+    - type: pass@1
+      value: 71.21
+      name: pass@1
+    - type: pass@1
+      value: 82.61
+      name: pass@1
+    - type: pass@1
+      value: 77.51
+      name: pass@1
+    - type: pass@1
+      value: 60.32
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: BoolQ
+      type: reading-comprehension
+    metrics:
+    - type: pass@1
+      value: 88.65
+      name: pass@1
+    - type: pass@1
+      value: 21.58
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC-C
+      type: reasoning
+    metrics:
+    - type: pass@1
+      value: 64.16
+      name: pass@1
+    - type: pass@1
+      value: 33.81
+      name: pass@1
+    - type: pass@1
+      value: 51.55
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis
+      type: code
+    metrics:
+    - type: pass@1
+      value: 64.63
+      name: pass@1
+    - type: pass@1
+      value: 57.16
+      name: pass@1
+    - type: pass@1
+      value: 65.85
+      name: pass@1
+    - type: pass@1
+      value: 49.6
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: GSM8K
+      type: math
+    metrics:
+    - type: pass@1
+      value: 68.99
+      name: pass@1
+    - type: pass@1
+      value: 30.94
+      name: pass@1
+  - task:
+      type: text-generation
+    dataset:
+      name: PAWS-X (7 langs)
+      type: multilingual
+    metrics:
+    - type: pass@1
+      value: 64.94
+      name: pass@1
+    - type: pass@1
+      value: 48.2
+      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-3.0-8b-instruct - GGUF
+
+This repo contains GGUF format model files for [ibm-granite/granite-3.0-8b-instruct](https://huggingface.co/ibm-granite/granite-3.0-8b-instruct).
+
+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
+
+```
+<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|>
+<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|>
+<|start_of_role|>assistant<|end_of_role|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [granite-3.0-8b-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q2_K.gguf) | Q2_K | 2.890 GB | smallest, significant quality loss - not recommended for most purposes |
+| [granite-3.0-8b-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q3_K_S.gguf) | Q3_K_S | 3.346 GB | very small, high quality loss |
+| [granite-3.0-8b-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q3_K_M.gguf) | Q3_K_M | 3.722 GB | very small, high quality loss |
+| [granite-3.0-8b-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q3_K_L.gguf) | Q3_K_L | 4.051 GB | small, substantial quality loss |
+| [granite-3.0-8b-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q4_0.gguf) | Q4_0 | 4.331 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [granite-3.0-8b-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q4_K_S.gguf) | Q4_K_S | 4.364 GB | small, greater quality loss |
+| [granite-3.0-8b-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q4_K_M.gguf) | Q4_K_M | 4.603 GB | medium, balanced quality - recommended |
+| [granite-3.0-8b-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q5_0.gguf) | Q5_0 | 5.259 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [granite-3.0-8b-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q5_K_S.gguf) | Q5_K_S | 5.259 GB | large, low quality loss - recommended |
+| [granite-3.0-8b-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q5_K_M.gguf) | Q5_K_M | 5.399 GB | large, very low quality loss - recommended |
+| [granite-3.0-8b-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q6_K.gguf) | Q6_K | 6.245 GB | very large, extremely low quality loss |
+| [granite-3.0-8b-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/granite-3.0-8b-instruct-GGUF/tree/main/granite-3.0-8b-instruct-Q8_0.gguf) | Q8_0 | 8.088 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-3.0-8b-instruct-GGUF --include "granite-3.0-8b-instruct-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-3.0-8b-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

granite-3.0-8b-instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9756977625b2c2f0b696dd6a13c4b2c558d117e9a3cbff2aee63a89ab33d153f
+size 3103588576

granite-3.0-8b-instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387326198eca75979a1f11942807eea022b53763f47f7e46ca34667d161c4935
+size 4349427936

granite-3.0-8b-instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16dab975fafd4694cce96450b22f6d712867dffba60cdef64aa51715f6f6c346
+size 3996582112

granite-3.0-8b-instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec0ea5653ddc950b4114d72c868db7c7b384d880205cc1c04ca9a0dee436766
+size 3592487136

granite-3.0-8b-instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a546d89aea85a98eee1029a26042b66f7ef12f7c2709a4b175d6ac5d5cd71a8f
+size 4650893536

granite-3.0-8b-instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b149699e5d40a5a18c78f1868f462b216a164e6b377ace3e4aa8391461e81b
+size 4942856416

granite-3.0-8b-instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89190a66806a1aa328b9d921dbc28a369a44be676056a87b10bda783d11dc5fa
+size 4685758688

granite-3.0-8b-instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1761e3cfd23a89465cf30845a750693b4be5be460d1523a4b08f89cce4598144
+size 5647040736

granite-3.0-8b-instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6d0526840d074edb2dd87b5cb122a463f3ed2dd434e576c750ed8c4e00c60b
+size 5797445856

granite-3.0-8b-instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51387df0ffc2098b33c83ba2e0e30af488f26e615b6ef035b6110d5acd3f5eb2
+size 5647040736

granite-3.0-8b-instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7daebcb72a24ccc8c83173d391afd24cf23b3399dc4d57f27b08ff144ea35a
+size 6705447136

granite-3.0-8b-instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ac480e15eeaf4b4692875cb91fd7cf787963fe9a06bc17e762a8ee29337a1a
+size 8684244096