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
+Beyonder-4x7B-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Beyonder-4x7B-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Beyonder-4x7B-v2-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2210812da25fbc64038ddf3c2645816459925e5c36b2515bd2dd1bf7231f7cad
+size 8842930304

Beyonder-4x7B-v2-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f30b7d14973b4268fd5a4e54cc966b7f8a6a99d714fec66f3ac79d5dc4c6c6
+size 12544084096

Beyonder-4x7B-v2-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ef15acb7206681c0a0ab72d8f030f2e42402182f1bc81f6abdc0dc78a38459
+size 11580442752

Beyonder-4x7B-v2-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0ab29f3b1ee86cfeb80c4ba360ac90597a27360ebc564c4b6bb23d3282733c
+size 10433300608

Beyonder-4x7B-v2-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8de2dcdfba2c0279f0944be0e913cfe5f9ba0c25110950a262c31341a45226
+size 13623699584

Beyonder-4x7B-v2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e8e539028f656366c8d1f98a35e2a1b9c76a334b65579cf98eba0d5c6f8e66
+size 14609885312

Beyonder-4x7B-v2-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8a51b551a813b90fd6b446af5ddf6487b31bad49543b8716a87364501ac8d6
+size 13743237248

Beyonder-4x7B-v2-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6169d114cce992ec37372022491bc81c2d512f683732f6841f7a45079b254db8
+size 16626428032

Beyonder-4x7B-v2-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f10ba59c28b99d272720f78d03d250369039cf7302f889f34a178811aa3d54
+size 17134463104

Beyonder-4x7B-v2-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53cdf806d2aac2506b9e057a3e9b2c5575175f3ae68ade9d2042e6a5608488b
+size 16626428032

Beyonder-4x7B-v2-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334b32fc720ba9d97e4a0ac62ac70ea24a01118578fc76596c2c6f4d34f84ea4
+size 19816827008

Beyonder-4x7B-v2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded15d9b8d9a495e485bcc0749b7919411f285897caa506a9aa14d6a1eeebf5d
+size 25666357376

README.md

@@ -0,0 +1,189 @@
+---
+license: other
+tags:
+- moe
+- merge
+- mergekit
+- Mistral
+- openchat/openchat-3.5-1210
+- beowolx/CodeNinja-1.0-OpenChat-7B
+- maywell/PiVoT-0.1-Starling-LM-RP
+- WizardLM/WizardMath-7B-V1.1
+- TensorBlock
+- GGUF
+license_name: microsoft-research-license
+license_link: https://huggingface.co/WizardLM/WizardMath-7B-V1.1/resolve/main/LICENSE
+base_model: mlabonne/Beyonder-4x7B-v2
+model-index:
+- name: Beyonder-4x7B-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: 68.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beyonder-4x7B-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: 86.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beyonder-4x7B-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: 65.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beyonder-4x7B-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: 60.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beyonder-4x7B-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: 80.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beyonder-4x7B-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: 71.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beyonder-4x7B-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>
+
+## mlabonne/Beyonder-4x7B-v2 - GGUF
+
+This repo contains GGUF format model files for [mlabonne/Beyonder-4x7B-v2](https://huggingface.co/mlabonne/Beyonder-4x7B-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
+
+```
+<s>GPT4 Correct System: {system_prompt}</s>GPT4 Correct User: {prompt}</s>GPT4 Correct Assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Beyonder-4x7B-v2-Q2_K.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q2_K.gguf) | Q2_K | 8.843 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Beyonder-4x7B-v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q3_K_S.gguf) | Q3_K_S | 10.433 GB | very small, high quality loss |
+| [Beyonder-4x7B-v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q3_K_M.gguf) | Q3_K_M | 11.580 GB | very small, high quality loss |
+| [Beyonder-4x7B-v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q3_K_L.gguf) | Q3_K_L | 12.544 GB | small, substantial quality loss |
+| [Beyonder-4x7B-v2-Q4_0.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q4_0.gguf) | Q4_0 | 13.624 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Beyonder-4x7B-v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q4_K_S.gguf) | Q4_K_S | 13.743 GB | small, greater quality loss |
+| [Beyonder-4x7B-v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q4_K_M.gguf) | Q4_K_M | 14.610 GB | medium, balanced quality - recommended |
+| [Beyonder-4x7B-v2-Q5_0.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q5_0.gguf) | Q5_0 | 16.626 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Beyonder-4x7B-v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q5_K_S.gguf) | Q5_K_S | 16.626 GB | large, low quality loss - recommended |
+| [Beyonder-4x7B-v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q5_K_M.gguf) | Q5_K_M | 17.134 GB | large, very low quality loss - recommended |
+| [Beyonder-4x7B-v2-Q6_K.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q6_K.gguf) | Q6_K | 19.817 GB | very large, extremely low quality loss |
+| [Beyonder-4x7B-v2-Q8_0.gguf](https://huggingface.co/tensorblock/Beyonder-4x7B-v2-GGUF/blob/main/Beyonder-4x7B-v2-Q8_0.gguf) | Q8_0 | 25.666 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/Beyonder-4x7B-v2-GGUF --include "Beyonder-4x7B-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/Beyonder-4x7B-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```