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
+saiga_gemma2_9b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_gemma2_9b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,121 @@
+---
+language:
+- ru
+datasets:
+- IlyaGusev/saiga_scored
+- IlyaGusev/saiga_preferences
+license: gemma
+tags:
+- TensorBlock
+- GGUF
+base_model: IlyaGusev/saiga_gemma2_9b
+---
+
+<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>
+
+## IlyaGusev/saiga_gemma2_9b - GGUF
+
+This repo contains GGUF format model files for [IlyaGusev/saiga_gemma2_9b](https://huggingface.co/IlyaGusev/saiga_gemma2_9b).
+
+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
+
+```
+<bos><start_of_turn>system
+{system_prompt}<end_of_turn>
+<start_of_turn>user
+{prompt}<end_of_turn>
+<start_of_turn>model
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [saiga_gemma2_9b-Q2_K.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q2_K.gguf) | Q2_K | 3.805 GB | smallest, significant quality loss - not recommended for most purposes |
+| [saiga_gemma2_9b-Q3_K_S.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q3_K_S.gguf) | Q3_K_S | 4.338 GB | very small, high quality loss |
+| [saiga_gemma2_9b-Q3_K_M.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q3_K_M.gguf) | Q3_K_M | 4.762 GB | very small, high quality loss |
+| [saiga_gemma2_9b-Q3_K_L.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q3_K_L.gguf) | Q3_K_L | 5.132 GB | small, substantial quality loss |
+| [saiga_gemma2_9b-Q4_0.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q4_0.gguf) | Q4_0 | 5.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [saiga_gemma2_9b-Q4_K_S.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q4_K_S.gguf) | Q4_K_S | 5.479 GB | small, greater quality loss |
+| [saiga_gemma2_9b-Q4_K_M.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q4_K_M.gguf) | Q4_K_M | 5.761 GB | medium, balanced quality - recommended |
+| [saiga_gemma2_9b-Q5_0.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q5_0.gguf) | Q5_0 | 6.484 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [saiga_gemma2_9b-Q5_K_S.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q5_K_S.gguf) | Q5_K_S | 6.484 GB | large, low quality loss - recommended |
+| [saiga_gemma2_9b-Q5_K_M.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q5_K_M.gguf) | Q5_K_M | 6.647 GB | large, very low quality loss - recommended |
+| [saiga_gemma2_9b-Q6_K.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q6_K.gguf) | Q6_K | 7.589 GB | very large, extremely low quality loss |
+| [saiga_gemma2_9b-Q8_0.gguf](https://huggingface.co/tensorblock/IlyaGusev_saiga_gemma2_9b-GGUF/blob/main/saiga_gemma2_9b-Q8_0.gguf) | Q8_0 | 9.827 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/IlyaGusev_saiga_gemma2_9b-GGUF --include "saiga_gemma2_9b-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/IlyaGusev_saiga_gemma2_9b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

saiga_gemma2_9b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9148188de1111360be15fa0f4178e90e0d35866069516182bf0923f50ae832
+size 3805398112

saiga_gemma2_9b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416d45546db40ad06775a37c0930aea9ab02bf8aa030d54b7959c42a3bc49b4e
+size 5132452960

saiga_gemma2_9b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a19505480a41f20a0f12b2784cb68872d0097ab94046aaf810a8e9bddf42b3
+size 4761781344

saiga_gemma2_9b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaeb86a29288ded5ee346ea928396a6d7386bafe317c7b5397a4f4e909119a7e
+size 4337665120

saiga_gemma2_9b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70240e17aec89c3d6aa0a759c98d6b00370991450a1adb54d47be0bb3b7198a
+size 5443142752

saiga_gemma2_9b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bf918c185878940d4d62b44d7d1d31c428c503278922edd861b6a8f74bf3f4
+size 5761057888

saiga_gemma2_9b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1342f83e8c95924a3f8efd2b26299c02557e5c322d2e7d53d0ee44ecc1ac8d
+size 5478925408

saiga_gemma2_9b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad175537e53758eaede095f1e099103b70d0171f639315200ea76701412901a
+size 6483592288

saiga_gemma2_9b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66753e9cbe870622d3d9e18d55cbb92828d3a4b482c9e38c892c30336a5f1b07
+size 6647366752

saiga_gemma2_9b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fbe0dd41fe690c877c158b70ec56431dd60eeb10bb4f69012cfd59e1f1748f
+size 6483592288

saiga_gemma2_9b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd822599dcb46245a757d832756887686beae5d2f91946edfcea3bae840c09d
+size 7589069920

saiga_gemma2_9b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277b66112e792634e567aba22691288e522855585913d92464eaf611e94c216f
+size 9827148896