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

README.md

@@ -0,0 +1,190 @@
+---
+language:
+- en
+license: cc-by-nc-sa-4.0
+datasets:
+- kyujinpy/orca_math_dpo
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
+model-index:
+- name: Sakura-SOLRCA-Math-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: 71.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-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: 88.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-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: 66.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-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: 72.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-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: 83.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-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: 63.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLRCA-Math-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-SOLRCA-Math-Instruct-DPO-v2 - GGUF
+
+This repo contains GGUF format model files for [kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Math-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 b4242](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
+
+```
+### System:
+{system_prompt}
+
+### User:
+{prompt}
+
+### Assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q2_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q2_K.gguf) | Q2_K | 4.003 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_S.gguf) | Q3_K_S | 4.665 GB | very small, high quality loss |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_M.gguf) | Q3_K_M | 5.196 GB | very small, high quality loss |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_L.gguf) | Q3_K_L | 5.651 GB | small, substantial quality loss |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_0.gguf) | Q4_0 | 6.072 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_K_S.gguf) | Q4_K_S | 6.119 GB | small, greater quality loss |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_K_M.gguf) | Q4_K_M | 6.462 GB | medium, balanced quality - recommended |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_0.gguf) | Q5_0 | 7.397 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_K_S.gguf) | Q5_K_S | 7.397 GB | large, low quality loss - recommended |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_K_M.gguf) | Q5_K_M | 7.598 GB | large, very low quality loss - recommended |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q6_K.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q6_K.gguf) | Q6_K | 8.805 GB | very large, extremely low quality loss |
+| [Sakura-SOLRCA-Math-Instruct-DPO-v2-Q8_0.gguf](https://huggingface.co/tensorblock/Sakura-SOLRCA-Math-Instruct-DPO-v2-GGUF/blob/main/Sakura-SOLRCA-Math-Instruct-DPO-v2-Q8_0.gguf) | Q8_0 | 11.404 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-SOLRCA-Math-Instruct-DPO-v2-GGUF --include "Sakura-SOLRCA-Math-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-SOLRCA-Math-Instruct-DPO-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236698b4bf21ef5cc49a379978031259de351812c4fba921ef91a0fb6c7b8471
+size 4003233088

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfbaeea8272a95117a34f5a532999e42bbbff45b2d8767daaf1f5e6ca4f3ba3
+size 5650750784

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12a2ba839d99a14dfc0b49dd5506b28d77dfdb33eafdff05b863606b3fb0645
+size 5195668800

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88baa5574577adaea7f85f748b796d99769ee27d65c1807eca85a94cb3f55cf
+size 4664565056

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e2f603f285cda41f5a155278d2ca60075b15332754eff7c5037a8ef6960a2e
+size 6072384832

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:757fc37ac90a3fa30e8e6ad4a8d84b26e699415f66f9dd1a7ad8de650355e47c
+size 6461668672

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246d59eabe1c8e92b1dc51a4c79f9d1be5b0df312bb03938b6446abae020d690
+size 6118522176

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45240cefdf16da27f2529338ded083d6eac6796bb7e4c550f7e496fff195d33
+size 7397391680

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76016c9e9e6a03f695a0afcbf82faa9972ece8239361e0695a82a444ef2a9ecc
+size 7597931840

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9bbb198881fd641c5684f67046c72102e588611da58e81ebb4865c3eee63f7
+size 7397391680

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bde5aed10910855bfe6f8b4fdf08ad0935f051d336ad7805294805be243706b
+size 8805211456

Sakura-SOLRCA-Math-Instruct-DPO-v2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8dd7c025a872c2a01acd78e8d938ccbf6bde4fcf852f5ac063257027c88b3f
+size 11404156224