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
+PowerMoE-3b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+PowerMoE-3b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

PowerMoE-3b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96efe630162af74048c2ec93e75da753b110a8d168abae99bba9a616da2c1c65
+size 1266132992

PowerMoE-3b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc474834d5756876288855614ff0ea5ee3acdaeac552ad6148547da4de3f7ef3
+size 1773971456

PowerMoE-3b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85fe7b3ccb8e12740eed6a44f6dd2209b44060f1bc1a9fcf44aacdb59353bec5
+size 1643620352

PowerMoE-3b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3557f70a73bafa744a0bccbd946c576e0ac12230e08ba671d365ae5800922280
+size 1488496640

PowerMoE-3b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100311f90e3ebf5a50183b07043ce07c6f1b18d7ed77e4db1e6a2f2c98b3f682
+size 1926342656

PowerMoE-3b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4ee188398c485364e77f1081b8f9533911e493e632c8757a239f77f1f3d3ed
+size 2059347968

PowerMoE-3b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bc35bdbcca546ed13a9791c8b9ab6a643d0ed9cca3a34b58e3e0dcfd5faf12
+size 1942464512

PowerMoE-3b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868b14ae122d3c5def3c1617aaa5a229b6788899a308e42eab9ecf7b8e761e7a
+size 2338433024

PowerMoE-3b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ccf45460f0af93f387492d6be79b4fc3facea1a89a7d35c0bfa8ce7d62bbe2
+size 2406950912

PowerMoE-3b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac18eea8a2f853155ff17c87ec8032f510c10c1d38b0c5a5f254430a301dbf5d
+size 2338433024

PowerMoE-3b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8124bd3855cb8d686910b840235f9acf5942c6618f724d9ed818702b9f7e33c1
+size 2776279040

PowerMoE-3b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06a4664bbc75551549ee34057ceddc1c6eb9d8e7dc38a4f519b760671708bb1
+size 3592988672

README.md

@@ -0,0 +1,174 @@
+---
+pipeline_tag: text-generation
+inference: false
+license: apache-2.0
+library_name: transformers
+tags:
+- TensorBlock
+- GGUF
+base_model: ibm-research/PowerMoE-3b
+model-index:
+- name: ibm/PowerMoE-3b
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: ARC
+      type: lm-eval-harness
+    metrics:
+    - type: accuracy-norm
+      value: 58.1
+      name: accuracy-norm
+      verified: false
+    - type: accuracy
+      value: 65.0
+      name: accuracy
+      verified: false
+    - type: accuracy-norm
+      value: 71.5
+      name: accuracy-norm
+      verified: false
+    - type: accuracy-norm
+      value: 41.0
+      name: accuracy-norm
+      verified: false
+    - type: accuracy-norm
+      value: 79.1
+      name: accuracy-norm
+      verified: false
+    - type: accuracy-norm
+      value: 65.0
+      name: accuracy-norm
+      verified: false
+    - type: accuracy
+      value: 42.8
+      name: accuracy
+      verified: false
+    - type: accuracy
+      value: 25.9
+      name: accuracy
+      verified: false
+    - type: accuracy
+      value: 14.8
+      name: accuracy
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: humaneval
+      type: bigcode-eval
+    metrics:
+    - type: pass@1
+      value: 20.1
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 32.4
+      name: pass@1
+      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-research/PowerMoE-3b - GGUF
+
+This repo contains GGUF format model files for [ibm-research/PowerMoE-3b](https://huggingface.co/ibm-research/PowerMoE-3b).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).
+
+## Our projects
+<table border="1" cellspacing="0" cellpadding="10">
+<tr>
+  <th style="font-size: 25px;">Awesome MCP Servers</th>
+  <th style="font-size: 25px;">TensorBlock Studio</th>
+</tr>
+  <tr>
+    <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
+    <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
+  </tr>
+  <tr>
+    <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
+    <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
+  </tr>
+<tr>
+  <th>
+    <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
+      display: inline-block;
+      padding: 8px 16px;
+      background-color: #FF7F50;
+      color: white;
+      text-decoration: none;
+      border-radius: 6px;
+      font-weight: bold;
+      font-family: sans-serif;
+    ">👀 See what we built 👀</a>
+  </th>
+  <th>
+    <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
+      display: inline-block;
+      padding: 8px 16px;
+      background-color: #FF7F50;
+      color: white;
+      text-decoration: none;
+      border-radius: 6px;
+      font-weight: bold;
+      font-family: sans-serif;
+    ">👀 See what we built 👀</a>
+  </th>
+</tr>
+</table>
+
+## Prompt template
+
+```
+Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [PowerMoE-3b-Q2_K.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q2_K.gguf) | Q2_K | 1.266 GB | smallest, significant quality loss - not recommended for most purposes |
+| [PowerMoE-3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q3_K_S.gguf) | Q3_K_S | 1.488 GB | very small, high quality loss |
+| [PowerMoE-3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q3_K_M.gguf) | Q3_K_M | 1.644 GB | very small, high quality loss |
+| [PowerMoE-3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q3_K_L.gguf) | Q3_K_L | 1.774 GB | small, substantial quality loss |
+| [PowerMoE-3b-Q4_0.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q4_0.gguf) | Q4_0 | 1.926 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [PowerMoE-3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q4_K_S.gguf) | Q4_K_S | 1.942 GB | small, greater quality loss |
+| [PowerMoE-3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q4_K_M.gguf) | Q4_K_M | 2.059 GB | medium, balanced quality - recommended |
+| [PowerMoE-3b-Q5_0.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q5_0.gguf) | Q5_0 | 2.338 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [PowerMoE-3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q5_K_S.gguf) | Q5_K_S | 2.338 GB | large, low quality loss - recommended |
+| [PowerMoE-3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q5_K_M.gguf) | Q5_K_M | 2.407 GB | large, very low quality loss - recommended |
+| [PowerMoE-3b-Q6_K.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q6_K.gguf) | Q6_K | 2.776 GB | very large, extremely low quality loss |
+| [PowerMoE-3b-Q8_0.gguf](https://huggingface.co/tensorblock/ibm-research_PowerMoE-3b-GGUF/blob/main/PowerMoE-3b-Q8_0.gguf) | Q8_0 | 3.593 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/ibm-research_PowerMoE-3b-GGUF --include "PowerMoE-3b-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/ibm-research_PowerMoE-3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```