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_11Bx2_MoE_19B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_11Bx2_MoE_19B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Mixtral_11Bx2_MoE_19B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063f766ec111675ae797ab7ee1f85bd79e9061ab1137749da632c3e08bf633fa
+size 7065604032

Mixtral_11Bx2_MoE_19B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be957fb64e0e76cd3478e3d25c095967a349ea195dd0532212b86e9c90782d6
+size 10012307392

Mixtral_11Bx2_MoE_19B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0090dc0fa10ca37cbd45da383319e425a3e7f0e0efdc231940dd66d5dd9523fa
+size 9226923968

Mixtral_11Bx2_MoE_19B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7586b16c92aaaafbc9cf16d0cab8d856050042e5c16a61f9814266b0792bd1b
+size 8299458496

Mixtral_11Bx2_MoE_19B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d91a6d8c4da2ac5b6b13437ee7e20c8cb69020db923e90451f87a3bda78555d
+size 10830303168

Mixtral_11Bx2_MoE_19B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871acdd2d2a3a7f73abd77a5197af74b4e57713fad8bff8d621358bbd51378ea
+size 11582918592

Mixtral_11Bx2_MoE_19B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91288148893e0933eefbaa0ede8c401b10e5ce80241d5a92cb2db765604bb1a
+size 10920480704

Mixtral_11Bx2_MoE_19B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9ec97fcce4b574d79fe580f1c9939575854d120fbb0dd309a29464ad2aca21
+size 13212274624

Mixtral_11Bx2_MoE_19B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b150c7b784b88eb98826fac6dadff0676d96298ee66a50a4d65fbdd122af4592
+size 13599985600

Mixtral_11Bx2_MoE_19B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4664a2575421095df48f6d6be8764788e7ee527d3e1d9f16a7705edcd8abecfe
+size 13212274624

Mixtral_11Bx2_MoE_19B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b8c223cb6d2062b1c72b2f6aa2e094c2452c02e0cc5944ca98efd77d172996
+size 15743119296

Mixtral_11Bx2_MoE_19B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889dc4513eec32c88a865d5a8c967ff9a8d0bc2c79591663fd3808e1faec3569
+size 20389932992

README.md

@@ -0,0 +1,185 @@
+---
+license: cc-by-nc-4.0
+base_model: cloudyu/Mixtral_11Bx2_MoE_19B
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: Mixtral_11Bx2_MoE_19B
+  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: 71.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_11Bx2_MoE_19B
+      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: 88.47
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_11Bx2_MoE_19B
+      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: 66.31
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_11Bx2_MoE_19B
+      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: 72.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_11Bx2_MoE_19B
+      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: 83.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_11Bx2_MoE_19B
+      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: 65.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral_11Bx2_MoE_19B
+      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_11Bx2_MoE_19B - GGUF
+
+This repo contains GGUF format model files for [cloudyu/Mixtral_11Bx2_MoE_19B](https://huggingface.co/cloudyu/Mixtral_11Bx2_MoE_19B).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [Mixtral_11Bx2_MoE_19B-Q2_K.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q2_K.gguf) | Q2_K | 7.066 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Mixtral_11Bx2_MoE_19B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q3_K_S.gguf) | Q3_K_S | 8.299 GB | very small, high quality loss |
+| [Mixtral_11Bx2_MoE_19B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q3_K_M.gguf) | Q3_K_M | 9.227 GB | very small, high quality loss |
+| [Mixtral_11Bx2_MoE_19B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q3_K_L.gguf) | Q3_K_L | 10.012 GB | small, substantial quality loss |
+| [Mixtral_11Bx2_MoE_19B-Q4_0.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q4_0.gguf) | Q4_0 | 10.830 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Mixtral_11Bx2_MoE_19B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q4_K_S.gguf) | Q4_K_S | 10.920 GB | small, greater quality loss |
+| [Mixtral_11Bx2_MoE_19B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q4_K_M.gguf) | Q4_K_M | 11.583 GB | medium, balanced quality - recommended |
+| [Mixtral_11Bx2_MoE_19B-Q5_0.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q5_0.gguf) | Q5_0 | 13.212 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Mixtral_11Bx2_MoE_19B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q5_K_S.gguf) | Q5_K_S | 13.212 GB | large, low quality loss - recommended |
+| [Mixtral_11Bx2_MoE_19B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q5_K_M.gguf) | Q5_K_M | 13.600 GB | large, very low quality loss - recommended |
+| [Mixtral_11Bx2_MoE_19B-Q6_K.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q6_K.gguf) | Q6_K | 15.743 GB | very large, extremely low quality loss |
+| [Mixtral_11Bx2_MoE_19B-Q8_0.gguf](https://huggingface.co/tensorblock/Mixtral_11Bx2_MoE_19B-GGUF/blob/main/Mixtral_11Bx2_MoE_19B-Q8_0.gguf) | Q8_0 | 20.390 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_11Bx2_MoE_19B-GGUF --include "Mixtral_11Bx2_MoE_19B-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_11Bx2_MoE_19B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```