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
+FusionNet_7Bx2_MoE_14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_7Bx2_MoE_14B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

FusionNet_7Bx2_MoE_14B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdbdc60c92addd58564e27fa3aeec0f0a6dc130e4b18993866b860cb7f64883
+size 4760823232

FusionNet_7Bx2_MoE_14B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d65071c1034eba683a23844c9d656fbf2957c8819384cd12f6aa1ccdfb55c1
+size 6729729472

FusionNet_7Bx2_MoE_14B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ae585e4b562b679874f948df202ee7fb1d480709527f2d6ea86c1cefe0fbf1
+size 6206490048

FusionNet_7Bx2_MoE_14B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c9a2ef14f59c60fd2f29e6cea481f7ef871c9e8d37f8355e418e94d3bacba0
+size 5587830208

FusionNet_7Bx2_MoE_14B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99c4fc6215d7ed4cbebd0fbfbbacece189f9732812c733264b111b52c6e1511
+size 7280862656

FusionNet_7Bx2_MoE_14B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23351ce4681b30ccdb0a1afeb7fd98fea5fa913768ef403e90ee38470bf281c3
+size 7782606272

FusionNet_7Bx2_MoE_14B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0b9c9e2c80a10add9ca280e1189392d104f6f2f116089ee2daebfc2e64c5fb
+size 7341680064

FusionNet_7Bx2_MoE_14B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e786b84a536f678f55761fc100a631127bdcca8968e283acb269ede37825e31f
+size 8874304960

FusionNet_7Bx2_MoE_14B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a1f4b8db8af483aed7a7a8e50bc53e5344d5e14e8b72f803dba9e2a02c3273
+size 9132778944

FusionNet_7Bx2_MoE_14B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03db02e4fdb862c6798b2203cde7448e50db501213d881c8a4739b82a43ee60
+size 8874304960

FusionNet_7Bx2_MoE_14B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642d13f8cc93d9a44096d2794fb20d3c9693b7c1cb37e0af1abe8b8db1905da8
+size 10567337408

FusionNet_7Bx2_MoE_14B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e6cbeea58f18ae26652cee991404e0a7f7edd4bfac01f0e65ae93f2565275a
+size 13686375872

README.md

@@ -0,0 +1,182 @@
+---
+language:
+- en
+license: mit
+tags:
+- moe
+- TensorBlock
+- GGUF
+base_model: TomGrc/FusionNet_7Bx2_MoE_14B
+model-index:
+- name: FusionNet_7Bx2_MoE_14B
+  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: 73.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_7Bx2_MoE_14B
+      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: 88.84
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_7Bx2_MoE_14B
+      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: 64.68
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_7Bx2_MoE_14B
+      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: 69.6
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_7Bx2_MoE_14B
+      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: 88.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_7Bx2_MoE_14B
+      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: 70.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_7Bx2_MoE_14B
+      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>
+
+## TomGrc/FusionNet_7Bx2_MoE_14B - GGUF
+
+This repo contains GGUF format model files for [TomGrc/FusionNet_7Bx2_MoE_14B](https://huggingface.co/TomGrc/FusionNet_7Bx2_MoE_14B).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [FusionNet_7Bx2_MoE_14B-Q2_K.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q2_K.gguf) | Q2_K | 4.761 GB | smallest, significant quality loss - not recommended for most purposes |
+| [FusionNet_7Bx2_MoE_14B-Q3_K_S.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q3_K_S.gguf) | Q3_K_S | 5.588 GB | very small, high quality loss |
+| [FusionNet_7Bx2_MoE_14B-Q3_K_M.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q3_K_M.gguf) | Q3_K_M | 6.206 GB | very small, high quality loss |
+| [FusionNet_7Bx2_MoE_14B-Q3_K_L.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q3_K_L.gguf) | Q3_K_L | 6.730 GB | small, substantial quality loss |
+| [FusionNet_7Bx2_MoE_14B-Q4_0.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q4_0.gguf) | Q4_0 | 7.281 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [FusionNet_7Bx2_MoE_14B-Q4_K_S.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q4_K_S.gguf) | Q4_K_S | 7.342 GB | small, greater quality loss |
+| [FusionNet_7Bx2_MoE_14B-Q4_K_M.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q4_K_M.gguf) | Q4_K_M | 7.783 GB | medium, balanced quality - recommended |
+| [FusionNet_7Bx2_MoE_14B-Q5_0.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q5_0.gguf) | Q5_0 | 8.874 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [FusionNet_7Bx2_MoE_14B-Q5_K_S.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q5_K_S.gguf) | Q5_K_S | 8.874 GB | large, low quality loss - recommended |
+| [FusionNet_7Bx2_MoE_14B-Q5_K_M.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q5_K_M.gguf) | Q5_K_M | 9.133 GB | large, very low quality loss - recommended |
+| [FusionNet_7Bx2_MoE_14B-Q6_K.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-Q6_K.gguf) | Q6_K | 10.567 GB | very large, extremely low quality loss |
+| [FusionNet_7Bx2_MoE_14B-Q8_0.gguf](https://huggingface.co/tensorblock/FusionNet_7Bx2_MoE_14B-GGUF/blob/main/FusionNet_7Bx2_MoE_14B-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/FusionNet_7Bx2_MoE_14B-GGUF --include "FusionNet_7Bx2_MoE_14B-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/FusionNet_7Bx2_MoE_14B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```