Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,16 @@ 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_34Bx2_MoE-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q8_0/FusionNet_34Bx2_MoE-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+FusionNet_34Bx2_MoE-Q8_0/FusionNet_34Bx2_MoE-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text

FusionNet_34Bx2_MoE-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6603277655f640e4845b809e7275fde96e5aa964adfc5c52d2dc482aa94b43e7
+size 22393660544

FusionNet_34Bx2_MoE-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a60a3561acc9a98f24e93699b6be349e91c911bf31ae92f8f43d7087d4a0200
+size 31767827584

FusionNet_34Bx2_MoE-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b33dd0e708c114909454e75e1031ee7501f45fdc496e5619a780d7dd9c6cc9
+size 29237351552

FusionNet_34Bx2_MoE-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30242a5957593ece7c656afa55c9652eb8895a9b4b2c622047db277f0d56eaeb
+size 26317853824

FusionNet_34Bx2_MoE-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bc54f93d49ac40ba083de949801999178a06114b64890f5ba2fc1e8b478eca
+size 34333541504

FusionNet_34Bx2_MoE-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770049185d7e9b99946387e1e3a9a52499912e37e42d41cdfc792a814cdf4aaf
+size 36661134464

FusionNet_34Bx2_MoE-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12547e9d2c10b6ec2cbff4d8305ba48b6e392014599b46a5518935f34ba04a1c
+size 34594112640

FusionNet_34Bx2_MoE-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d6c5aae31304c9aede62d0b1c3eee6a01a0cfd7eced7245a063255cb823f79
+size 41877718144

FusionNet_34Bx2_MoE-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e741da7b0cc7a711b038566bb123bf850db23175acf91839b7f744e569cf2b2
+size 43076781184

FusionNet_34Bx2_MoE-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900c102f680145478d86700f1dbc47863b07fc80901e741d70813ade8982b980
+size 41877718144

FusionNet_34Bx2_MoE-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f02a60f02e660f32452d68f0906d11a92a0df95854084adca629af54783306
+size 49893405824

FusionNet_34Bx2_MoE-Q8_0/FusionNet_34Bx2_MoE-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34751571072d7519fa7042505e0da1ea6a2a0a218ac8673b88806eae36f1be4
+size 34982772544

FusionNet_34Bx2_MoE-Q8_0/FusionNet_34Bx2_MoE-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a5a9a7e0ff539b839a9a52a2f1431c920ade2c8d07d1fc0e2552f7e0b94e85
+size 29638579744

README.md

@@ -0,0 +1,187 @@
+---
+language:
+- en
+license: mit
+tags:
+- moe
+- TensorBlock
+- GGUF
+pipeline_tag: text-generation
+base_model: TomGrc/FusionNet_34Bx2_MoE
+model-index:
+- name: FusionNet_34Bx2_MoE
+  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: 72.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_34Bx2_MoE
+      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: 86.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_34Bx2_MoE
+      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: 77.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_34Bx2_MoE
+      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: 71.31
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_34Bx2_MoE
+      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: 83.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_34Bx2_MoE
+      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: 70.89
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_34Bx2_MoE
+      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_34Bx2_MoE - GGUF
+
+This repo contains GGUF format model files for [TomGrc/FusionNet_34Bx2_MoE](https://huggingface.co/TomGrc/FusionNet_34Bx2_MoE).
+
+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
+
+```
+[INST] <<SYS>>
+{system_prompt}
+<</SYS>>
+
+{prompt} [/INST]
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [FusionNet_34Bx2_MoE-Q2_K.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q2_K.gguf) | Q2_K | 22.394 GB | smallest, significant quality loss - not recommended for most purposes |
+| [FusionNet_34Bx2_MoE-Q3_K_S.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q3_K_S.gguf) | Q3_K_S | 26.318 GB | very small, high quality loss |
+| [FusionNet_34Bx2_MoE-Q3_K_M.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q3_K_M.gguf) | Q3_K_M | 29.237 GB | very small, high quality loss |
+| [FusionNet_34Bx2_MoE-Q3_K_L.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q3_K_L.gguf) | Q3_K_L | 31.768 GB | small, substantial quality loss |
+| [FusionNet_34Bx2_MoE-Q4_0.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q4_0.gguf) | Q4_0 | 34.334 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [FusionNet_34Bx2_MoE-Q4_K_S.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q4_K_S.gguf) | Q4_K_S | 34.594 GB | small, greater quality loss |
+| [FusionNet_34Bx2_MoE-Q4_K_M.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q4_K_M.gguf) | Q4_K_M | 36.661 GB | medium, balanced quality - recommended |
+| [FusionNet_34Bx2_MoE-Q5_0.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q5_0.gguf) | Q5_0 | 41.878 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [FusionNet_34Bx2_MoE-Q5_K_S.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q5_K_S.gguf) | Q5_K_S | 41.878 GB | large, low quality loss - recommended |
+| [FusionNet_34Bx2_MoE-Q5_K_M.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q5_K_M.gguf) | Q5_K_M | 43.077 GB | large, very low quality loss - recommended |
+| [FusionNet_34Bx2_MoE-Q6_K.gguf](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q6_K.gguf) | Q6_K | 49.893 GB | very large, extremely low quality loss |
+| [FusionNet_34Bx2_MoE-Q8_0](https://huggingface.co/tensorblock/FusionNet_34Bx2_MoE-GGUF/blob/main/FusionNet_34Bx2_MoE-Q8_0) | Q8_0 | 64.621 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_34Bx2_MoE-GGUF --include "FusionNet_34Bx2_MoE-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_34Bx2_MoE-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```