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
+Sakura-SOLAR-Instruct-DPO-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Sakura-SOLAR-Instruct-DPO-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,184 @@
+---
+language:
+- en
+license: cc-by-nc-sa-4.0
+datasets:
+- argilla/distilabel-math-preference-dpo
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+model-index:
+- name: Sakura-SOLAR-Instruct-DPO-v2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 70.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 88.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 66.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 71.86
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 83.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct-DPO-v2
+      name: Open LLM Leaderboard
+---
+
+<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>
+
+## kyujinpy/Sakura-SOLAR-Instruct-DPO-v2 - GGUF
+
+This repo contains GGUF format model files for [kyujinpy/Sakura-SOLAR-Instruct-DPO-v2](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct-DPO-v2).
+
+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
+
+```
+### System:
+{system_prompt}
+
+### User:
+{prompt}
+
+### Assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q2_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q2_K.gguf) | Q2_K | 3.728 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q3_K_S.gguf) | Q3_K_S | 4.344 GB | very small, high quality loss |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q3_K_M.gguf) | Q3_K_M | 4.839 GB | very small, high quality loss |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q3_K_L.gguf) | Q3_K_L | 5.263 GB | small, substantial quality loss |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q4_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q4_0.gguf) | Q4_0 | 5.655 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q4_K_S.gguf) | Q4_K_S | 5.698 GB | small, greater quality loss |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q4_K_M.gguf) | Q4_K_M | 6.018 GB | medium, balanced quality - recommended |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q5_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q5_0.gguf) | Q5_0 | 6.889 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q5_K_S.gguf) | Q5_K_S | 6.889 GB | large, low quality loss - recommended |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q5_K_M.gguf) | Q5_K_M | 7.076 GB | large, very low quality loss - recommended |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q6_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q6_K.gguf) | Q6_K | 8.200 GB | very large, extremely low quality loss |
+| [Sakura-SOLAR-Instruct-DPO-v2-Q8_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLAR-Instruct-DPO-v2-GGUF/tree/main/Sakura-SOLAR-Instruct-DPO-v2-Q8_0.gguf) | Q8_0 | 10.621 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/Sakura-SOLAR-Instruct-DPO-v2-GGUF --include "Sakura-SOLAR-Instruct-DPO-v2-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/Sakura-SOLAR-Instruct-DPO-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Sakura-SOLAR-Instruct-DPO-v2-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0370d6749d142237d23dc7c141ccc1d07e85715bdfa8131c63df9b4882933d5
+size 4003232832

Sakura-SOLAR-Instruct-DPO-v2-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1af3783b69bb31773b0e0d55701c64a66e647d06dc74d9b7f5c88e1299de58a
+size 5650750528

Sakura-SOLAR-Instruct-DPO-v2-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e72a6184275c4b5b7e39b64579c7ca18da3d2ee75887e8867a6cd2fde1f6f2
+size 5195668544

Sakura-SOLAR-Instruct-DPO-v2-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d9f9d032fc47dbc5e598b779804dc6c3c29c2b90841aeae7e0adccfd5cf2d9
+size 4664564800

Sakura-SOLAR-Instruct-DPO-v2-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1294b49c8e938ac275ffe65c67d9d87681b53b5b1930c1fdfe5ea38b4359a83e
+size 6072384576

Sakura-SOLAR-Instruct-DPO-v2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ffc95ccf00f302594a5937f4d4dfba47780050c36a0db099378a083769e2c3
+size 6461668416

Sakura-SOLAR-Instruct-DPO-v2-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054484e0e2a847babc8a696411725a7f42363730c17d26b44db3e9706149f73d
+size 6118521920

Sakura-SOLAR-Instruct-DPO-v2-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f155ce78d447c1e108cc2809103bd8e0ca8892bd71b50caf3773b975a00247
+size 7397391424

Sakura-SOLAR-Instruct-DPO-v2-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd514daeb1094e8d7257ef60434830817e4e4518d5f6149aced56d15fd7a389
+size 7597931584

Sakura-SOLAR-Instruct-DPO-v2-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9a3cec1104c6ea04a6b3212729a63a20f985148b6cd8215b3f9722e8e4c5be
+size 7397391424

Sakura-SOLAR-Instruct-DPO-v2-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59603bb8c2c1e327f62f67c591757423e4d6e872f1d999e469210bccb38c3fc6
+size 8805211200

Sakura-SOLAR-Instruct-DPO-v2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de386f0936fecfe0417506f23b486607b9f1123df7746828250b7eb158a0665
+size 11404155968