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
+NeuralHermes-MoE-2x7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralHermes-MoE-2x7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

NeuralHermes-MoE-2x7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9759837fc7318b2e3542b937ebbc629f4a5ef86702f086ebf36eb23e18071179
+size 4760823296

NeuralHermes-MoE-2x7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2279d25d5f736a267ab5110e631692cdc5ae3d36af6c713ef0d6a75bce9017
+size 6729729536

NeuralHermes-MoE-2x7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863def2b33323f8d3df819469eaf0ba50824632410ed8e9575e1d28170953c7b
+size 6206490112

NeuralHermes-MoE-2x7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69289d2e08af9b003d4c281b40905a073aa39d31fec5734a76cb662175f07e9e
+size 5587830272

NeuralHermes-MoE-2x7B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c5af920296ee30103f1c5d375a49c459b6439d90604b341669cc9f16b5dc67
+size 7280862720

NeuralHermes-MoE-2x7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18407047a1d17b6b5b5ba7058bb174b232416ced19c413706e2e8d2c469754fe
+size 7782606336

NeuralHermes-MoE-2x7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74ad2fb7760520865cafa3b513fde676f3b106c0391e442e205b72d52f7e458
+size 7341680128

NeuralHermes-MoE-2x7B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6c4f4452e9d5ca48286ac52519a5f8eb77b68958692a7d8159a00f18b385e1
+size 8874305024

NeuralHermes-MoE-2x7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527320fd0e0460eb57fc26b29a099265e8101284b7a4a39b962e82a6f18472ee
+size 9132779008

NeuralHermes-MoE-2x7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f76bf3b7415348d17cfbdd9e053ded00fc143d0b8ffbeff2987a1c959c6d165
+size 8874305024

NeuralHermes-MoE-2x7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b350855f747d4e80a06c8f5867115dfafb8b935b3e6d16756f848f7da1ea7bf
+size 10567337472

NeuralHermes-MoE-2x7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0de75d8cf215fc3015b8fb88892a6abaf5764a3bae451e59caed576776b8eb6
+size 13686375936

README.md

@@ -0,0 +1,182 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- merge
+- TensorBlock
+- GGUF
+base_model: ibndias/NeuralHermes-MoE-2x7B
+model-index:
+- name: NeuralHermes-MoE-2x7B
+  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: 62.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 84.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 64.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 43.61
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 78.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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: 51.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B
+      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>
+
+## ibndias/NeuralHermes-MoE-2x7B - GGUF
+
+This repo contains GGUF format model files for [ibndias/NeuralHermes-MoE-2x7B](https://huggingface.co/ibndias/NeuralHermes-MoE-2x7B).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [NeuralHermes-MoE-2x7B-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q2_K.gguf) | Q2_K | 4.761 GB | smallest, significant quality loss - not recommended for most purposes |
+| [NeuralHermes-MoE-2x7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q3_K_S.gguf) | Q3_K_S | 5.588 GB | very small, high quality loss |
+| [NeuralHermes-MoE-2x7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q3_K_M.gguf) | Q3_K_M | 6.206 GB | very small, high quality loss |
+| [NeuralHermes-MoE-2x7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q3_K_L.gguf) | Q3_K_L | 6.730 GB | small, substantial quality loss |
+| [NeuralHermes-MoE-2x7B-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q4_0.gguf) | Q4_0 | 7.281 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [NeuralHermes-MoE-2x7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q4_K_S.gguf) | Q4_K_S | 7.342 GB | small, greater quality loss |
+| [NeuralHermes-MoE-2x7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q4_K_M.gguf) | Q4_K_M | 7.783 GB | medium, balanced quality - recommended |
+| [NeuralHermes-MoE-2x7B-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q5_0.gguf) | Q5_0 | 8.874 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [NeuralHermes-MoE-2x7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q5_K_S.gguf) | Q5_K_S | 8.874 GB | large, low quality loss - recommended |
+| [NeuralHermes-MoE-2x7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q5_K_M.gguf) | Q5_K_M | 9.133 GB | large, very low quality loss - recommended |
+| [NeuralHermes-MoE-2x7B-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q6_K.gguf) | Q6_K | 10.567 GB | very large, extremely low quality loss |
+| [NeuralHermes-MoE-2x7B-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralHermes-MoE-2x7B-GGUF/blob/main/NeuralHermes-MoE-2x7B-Q8_0.gguf) | Q8_0 | 13.686 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/NeuralHermes-MoE-2x7B-GGUF --include "NeuralHermes-MoE-2x7B-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/NeuralHermes-MoE-2x7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```