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

README.md

@@ -0,0 +1,87 @@
+---
+license: cc-by-nc-nd-4.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- starling
+- mistral
+- llama-2
+- TensorBlock
+- GGUF
+base_model: Delcos/Velara
+---
+
+<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>
+
+## Delcos/Velara - GGUF
+
+This repo contains GGUF format model files for [Delcos/Velara](https://huggingface.co/Delcos/Velara).
+
+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).
+
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
+
+## Prompt template
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Velara-Q2_K.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q2_K.gguf) | Q2_K | 3.953 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Velara-Q3_K_S.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q3_K_S.gguf) | Q3_K_S | 4.606 GB | very small, high quality loss |
+| [Velara-Q3_K_M.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q3_K_M.gguf) | Q3_K_M | 5.130 GB | very small, high quality loss |
+| [Velara-Q3_K_L.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q3_K_L.gguf) | Q3_K_L | 5.582 GB | small, substantial quality loss |
+| [Velara-Q4_0.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q4_0.gguf) | Q4_0 | 5.998 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Velara-Q4_K_S.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q4_K_S.gguf) | Q4_K_S | 6.041 GB | small, greater quality loss |
+| [Velara-Q4_K_M.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q4_K_M.gguf) | Q4_K_M | 6.376 GB | medium, balanced quality - recommended |
+| [Velara-Q5_0.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q5_0.gguf) | Q5_0 | 7.308 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Velara-Q5_K_S.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q5_K_S.gguf) | Q5_K_S | 7.308 GB | large, low quality loss - recommended |
+| [Velara-Q5_K_M.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q5_K_M.gguf) | Q5_K_M | 7.503 GB | large, very low quality loss - recommended |
+| [Velara-Q6_K.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q6_K.gguf) | Q6_K | 8.700 GB | very large, extremely low quality loss |
+| [Velara-Q8_0.gguf](https://huggingface.co/tensorblock/Velara-GGUF/blob/main/Velara-Q8_0.gguf) | Q8_0 | 11.269 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/Velara-GGUF --include "Velara-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/Velara-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Velara-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048ce50a56ccd47e13e5d00564617a207f1fc218ab0c00c8787a130994727a9a
+size 4243990048

Velara-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec9380b4bc9f9e2f6da1223bddceb9c846e689b7fe5101367f5fa5e0007ebb4
+size 5993646432

Velara-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7a1436a11c76b8506850ea5c2f18f8ffa8cc2b4d90fd2817638980d0e4fcb2
+size 5508680032

Velara-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4419f51c82128e94dc0fa3b8c70419d003d64fa71acd05ce6979ee10e72a94e7
+size 4945824096

Velara-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97be3ff36fcf0c497b6c18fd268423189c4db4c9576b2e2cef284a7767ab3c40
+size 6440545696

Velara-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce167611e25589f5e8825b2bb5b274e0d1ef8297c0a3ac8f4e8445c085544c7a
+size 6846049696

Velara-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdb8fdfc05f2efbf44f55dccf8e9b03bdd419a57cbfaef63492a106aee1e41f
+size 6486683040

Velara-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d006cfef427bd18bae85fcface510ee235bd448bd002e0e3d72dd06d665a9d
+size 7847342496

Velara-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac14a54fab99cc95998fa431b858add03c8eb1ab728333ab89d9792a5b93c8a
+size 8056238496

Velara-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60646f428163d7b48ace8f1027d1405c6fc2ce49114dd24466bff429a3716e30
+size 7847342496

Velara-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ba462c6b2f131b4f7d6c2f0d306328b6b88c102d0c69531084aa9a21ee899a
+size 9342064096

Velara-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe53f45e03c0e160f379cb24953a5e701a3ee023d4ffc02c6f6aa0bc8f67b6c
+size 12099478880