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
+EastAsia-4x7B-Moe-experiment-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+EastAsia-4x7B-Moe-experiment-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

EastAsia-4x7B-Moe-experiment-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9566ff9fa88e90df9ad765b512dcdd6d21ad231889c2facf289dac25b1d8d5
+size 6801876672

EastAsia-4x7B-Moe-experiment-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96755790ebfae3136c2581cebba050086fc6836b6ecda8bf18f4d2cd306a09f6
+size 9636906688

EastAsia-4x7B-Moe-experiment-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9672485a401c96b0f01cb3c423a926a976f0d12e10542313ad1dce7e2219b0c4
+size 8893466304

EastAsia-4x7B-Moe-experiment-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4046aec8d900553154ba8ee7da6dc8f6bac6cc4fbcf1212b5b82db0bf0576a29
+size 8010565312

EastAsia-4x7B-Moe-experiment-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4981c1f17288da9c9c5a7cd62365b98f5a81db806c4a48150344d9fced1ef0
+size 10452281024

EastAsia-4x7B-Moe-experiment-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ccd5242a7cfea03d42cb75241e3388eb2a0d57f5ef6ec0ac2b3c9e68464892
+size 11196245696

EastAsia-4x7B-Moe-experiment-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571b52a40fb69a9d2f603db4b690c19b878254bbb29a6ff11edd0f2ec6910c57
+size 10542458560

EastAsia-4x7B-Moe-experiment-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0da8164263dd270339e0cc6134aead918594bc60111f2f8d2f99330aa11b896
+size 12750366400

EastAsia-4x7B-Moe-experiment-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab93ee3d9ace8571da82a0a101efacc385815defd43b552db2034f25095e085a
+size 13133620928

EastAsia-4x7B-Moe-experiment-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566807625c275efef62faf17daa5f50b99ad0a16ab979d5aeaf0d7724d0bd356
+size 12750366400

EastAsia-4x7B-Moe-experiment-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e968d731236be06d8afaa1148e1788729b229d2d489c887186f241e5bd48b2
+size 15192082112

EastAsia-4x7B-Moe-experiment-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7345eb2a2859e2a22b80f51ee6f91aa6ee84bae4998d45eaa5a99eeb3c28ff17
+size 19676366528

README.md

@@ -0,0 +1,191 @@
+---
+language:
+- zh
+- ja
+- ko
+- tw
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- lazymergekit
+- MediaTek-Research/Breeze-7B-Instruct-v0.1
+- augmxnt/shisa-7b-v1
+- beomi/OPEN-SOLAR-KO-10.7B
+- TensorBlock
+- GGUF
+base_model: Heng666/EastAsia-4x7B-Moe-experiment
+model-index:
+- name: EastAsia-4x7B-Moe-experiment
+  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: 39.51
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 48.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 56.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 49.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 58.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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: 0.15
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Heng666/EastAsia-4x7B-Moe-experiment
+      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>
+
+## Heng666/EastAsia-4x7B-Moe-experiment - GGUF
+
+This repo contains GGUF format model files for [Heng666/EastAsia-4x7B-Moe-experiment](https://huggingface.co/Heng666/EastAsia-4x7B-Moe-experiment).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [EastAsia-4x7B-Moe-experiment-Q2_K.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q2_K.gguf) | Q2_K | 6.802 GB | smallest, significant quality loss - not recommended for most purposes |
+| [EastAsia-4x7B-Moe-experiment-Q3_K_S.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q3_K_S.gguf) | Q3_K_S | 8.011 GB | very small, high quality loss |
+| [EastAsia-4x7B-Moe-experiment-Q3_K_M.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q3_K_M.gguf) | Q3_K_M | 8.893 GB | very small, high quality loss |
+| [EastAsia-4x7B-Moe-experiment-Q3_K_L.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q3_K_L.gguf) | Q3_K_L | 9.637 GB | small, substantial quality loss |
+| [EastAsia-4x7B-Moe-experiment-Q4_0.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q4_0.gguf) | Q4_0 | 10.452 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [EastAsia-4x7B-Moe-experiment-Q4_K_S.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q4_K_S.gguf) | Q4_K_S | 10.542 GB | small, greater quality loss |
+| [EastAsia-4x7B-Moe-experiment-Q4_K_M.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q4_K_M.gguf) | Q4_K_M | 11.196 GB | medium, balanced quality - recommended |
+| [EastAsia-4x7B-Moe-experiment-Q5_0.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q5_0.gguf) | Q5_0 | 12.750 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [EastAsia-4x7B-Moe-experiment-Q5_K_S.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q5_K_S.gguf) | Q5_K_S | 12.750 GB | large, low quality loss - recommended |
+| [EastAsia-4x7B-Moe-experiment-Q5_K_M.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q5_K_M.gguf) | Q5_K_M | 13.134 GB | large, very low quality loss - recommended |
+| [EastAsia-4x7B-Moe-experiment-Q6_K.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q6_K.gguf) | Q6_K | 15.192 GB | very large, extremely low quality loss |
+| [EastAsia-4x7B-Moe-experiment-Q8_0.gguf](https://huggingface.co/tensorblock/EastAsia-4x7B-Moe-experiment-GGUF/blob/main/EastAsia-4x7B-Moe-experiment-Q8_0.gguf) | Q8_0 | 19.676 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/EastAsia-4x7B-Moe-experiment-GGUF --include "EastAsia-4x7B-Moe-experiment-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/EastAsia-4x7B-Moe-experiment-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```