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
+Mixtral_34Bx2_MoE_60B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_34Bx2_MoE_60B-Q8_0/Mixtral_34Bx2_MoE_60B-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text

Mixtral_34Bx2_MoE_60B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b5ac32507cf5c7d74b84a86a042e4eff8f6c415556d368b9d7bad77a3f554a
+size 22393660064

Mixtral_34Bx2_MoE_60B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dac24e88e70afbdad1ccaadfc3408ee58cf4d7128f378f116c11e3ba7bc80a3
+size 31767827104

Mixtral_34Bx2_MoE_60B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e332c8766029847dc9fb2d84ba8f87fcd63427da2584f2f7a4330b2a8aacb7a
+size 29237351072

Mixtral_34Bx2_MoE_60B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35805c733a73b3c00ee0b3af8e024b40f4f56f4654efe720d8f3a85334da18ce
+size 26317853344

Mixtral_34Bx2_MoE_60B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8464df56e5755c77af5a3e86f658bda7455bd13dfe635e8923383327008b74
+size 34333541024

Mixtral_34Bx2_MoE_60B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ca2a54d0d030ed5bd26435ce6883f921fdec605b5c922c9aa0cdd7cc96c261
+size 36661133984

Mixtral_34Bx2_MoE_60B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8a78e59fef8a0e1cddd0213c0af78cefe0fc922247140a3307064f5d3b5989
+size 34594112160

Mixtral_34Bx2_MoE_60B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ffe1f6474b6a6bf8b528e51753aacc4b9e2aaad65f8fe900c0361beec15b44
+size 41877717664

Mixtral_34Bx2_MoE_60B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951763279c79a55f5d827947bbde8d50c2d400da3ece4579629a86a1d8daad22
+size 43076780704

Mixtral_34Bx2_MoE_60B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd517e549fe50a43cd1841f30fbba0b645bae8902350ef1ca5e05144c7524f77
+size 41877717664

Mixtral_34Bx2_MoE_60B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0bbf2e0f447dcb5e2c63116e61696f3b77993f0a2f6f7aaba805f297578a17
+size 49893405344

Mixtral_34Bx2_MoE_60B-Q8_0/Mixtral_34Bx2_MoE_60B-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4b510e558cca99107106c89a14fd45c3cb5baa481a5b8aeb336c71073240e2
+size 959213568

README.md

@@ -0,0 +1,173 @@
+---
+license: apache-2.0
+tags:
+- yi
+- moe
+- TensorBlock
+- GGUF
+base_model: cloudyu/Mixtral_34Bx2_MoE_60B
+model-index:
+- name: Mixtral_34Bx2_MoE_60B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 45.38
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 41.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 6.57
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.74
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 17.78
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 41.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Mixtral_34Bx2_MoE_60B
+      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>
+
+## cloudyu/Mixtral_34Bx2_MoE_60B - GGUF
+
+This repo contains GGUF format model files for [cloudyu/Mixtral_34Bx2_MoE_60B](https://huggingface.co/cloudyu/Mixtral_34Bx2_MoE_60B).
+
+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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Mixtral_34Bx2_MoE_60B-Q2_K.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q2_K.gguf) | Q2_K | 22.394 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Mixtral_34Bx2_MoE_60B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q3_K_S.gguf) | Q3_K_S | 26.318 GB | very small, high quality loss |
+| [Mixtral_34Bx2_MoE_60B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q3_K_M.gguf) | Q3_K_M | 29.237 GB | very small, high quality loss |
+| [Mixtral_34Bx2_MoE_60B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q3_K_L.gguf) | Q3_K_L | 31.768 GB | small, substantial quality loss |
+| [Mixtral_34Bx2_MoE_60B-Q4_0.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q4_0.gguf) | Q4_0 | 34.334 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Mixtral_34Bx2_MoE_60B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q4_K_S.gguf) | Q4_K_S | 34.594 GB | small, greater quality loss |
+| [Mixtral_34Bx2_MoE_60B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q4_K_M.gguf) | Q4_K_M | 36.661 GB | medium, balanced quality - recommended |
+| [Mixtral_34Bx2_MoE_60B-Q5_0.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q5_0.gguf) | Q5_0 | 41.878 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Mixtral_34Bx2_MoE_60B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q5_K_S.gguf) | Q5_K_S | 41.878 GB | large, low quality loss - recommended |
+| [Mixtral_34Bx2_MoE_60B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q5_K_M.gguf) | Q5_K_M | 43.077 GB | large, very low quality loss - recommended |
+| [Mixtral_34Bx2_MoE_60B-Q6_K.gguf](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q6_K.gguf) | Q6_K | 49.893 GB | very large, extremely low quality loss |
+| [Mixtral_34Bx2_MoE_60B-Q8_0](https://huggingface.co/tensorblock/Mixtral_34Bx2_MoE_60B-GGUF/blob/main/Mixtral_34Bx2_MoE_60B-Q8_0) | Q8_0 | 0.959 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/Mixtral_34Bx2_MoE_60B-GGUF --include "Mixtral_34Bx2_MoE_60B-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/Mixtral_34Bx2_MoE_60B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```