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
+CantoneseLLM-6B-preview202402-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+CantoneseLLM-6B-preview202402-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

CantoneseLLM-6B-preview202402-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ea8a2611fbfc0b38964a1d4d19eb698241117a641ec56a3858db6758778c0d
+size 2337066912

CantoneseLLM-6B-preview202402-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074f21a14b5f939b0ade18a812baae42d0f8e5af670b6bb04ce188d1a86e48b2
+size 3236892576

CantoneseLLM-6B-preview202402-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4832722cee32026e8e17c4293893e40a76265205e5e266f4a4e3dda5067bc5
+size 2992836512

CantoneseLLM-6B-preview202402-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b311e5f36ba3d006d090be22d264635ddd425bc3d85b2845a5781ddd1f14a8b
+size 2709196704

CantoneseLLM-6B-preview202402-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41468b01861f83c48351a02d96eb15c2430d20df383db31fe1fb2d8d912b2525
+size 3479326624

CantoneseLLM-6B-preview202402-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79468f11ff701c6a37cc8a669b3b4cf26eff6728835abc28feceed279a4c9304
+size 3673968544

CantoneseLLM-6B-preview202402-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985749b157b6411f343afab88348a1e8d603dafce5cdad29cb9ab5ada77e5ca6
+size 3502919584

CantoneseLLM-6B-preview202402-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fb13534900128cb3d418f7f3d7648b6e59de9c551b0f829f17abddb00cd0fd
+size 4204154784

CantoneseLLM-6B-preview202402-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3ca4cfb9c62f3e12b23fb3b72b16a9ba11dddc22e944de6310b42b1fc3a8dc
+size 4304424864

CantoneseLLM-6B-preview202402-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb27c0b519c3167a425a81a0c5c7fc261ed8a902fd37e068801243c1c5b49052
+size 4204154784

CantoneseLLM-6B-preview202402-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2618cf964d03f451765d9366a591ca64c70e58047a330069f6e1225f93186c0
+size 4974284704

CantoneseLLM-6B-preview202402-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a19300a4651b4518625110ab993c4f0e535e5c2b5bf6bab8f934b964e57cd6c
+size 6442127264

README.md

@@ -0,0 +1,184 @@
+---
+language:
+- yue
+license: other
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: hon9kon9ize/CantoneseLLM-6B-preview202402
+model-index:
+- name: CantoneseLLM-6B-preview202402
+  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: 55.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLM-6B-preview202402
+      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: 75.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLM-6B-preview202402
+      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: 63.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLM-6B-preview202402
+      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: 42.26
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLM-6B-preview202402
+      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: 74.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLM-6B-preview202402
+      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: 30.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hon9kon9ize/CantoneseLLM-6B-preview202402
+      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>
+
+## hon9kon9ize/CantoneseLLM-6B-preview202402 - GGUF
+
+This repo contains GGUF format model files for [hon9kon9ize/CantoneseLLM-6B-preview202402](https://huggingface.co/hon9kon9ize/CantoneseLLM-6B-preview202402).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [CantoneseLLM-6B-preview202402-Q2_K.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q2_K.gguf) | Q2_K | 2.337 GB | smallest, significant quality loss - not recommended for most purposes |
+| [CantoneseLLM-6B-preview202402-Q3_K_S.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q3_K_S.gguf) | Q3_K_S | 2.709 GB | very small, high quality loss |
+| [CantoneseLLM-6B-preview202402-Q3_K_M.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q3_K_M.gguf) | Q3_K_M | 2.993 GB | very small, high quality loss |
+| [CantoneseLLM-6B-preview202402-Q3_K_L.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q3_K_L.gguf) | Q3_K_L | 3.237 GB | small, substantial quality loss |
+| [CantoneseLLM-6B-preview202402-Q4_0.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q4_0.gguf) | Q4_0 | 3.479 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [CantoneseLLM-6B-preview202402-Q4_K_S.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q4_K_S.gguf) | Q4_K_S | 3.503 GB | small, greater quality loss |
+| [CantoneseLLM-6B-preview202402-Q4_K_M.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q4_K_M.gguf) | Q4_K_M | 3.674 GB | medium, balanced quality - recommended |
+| [CantoneseLLM-6B-preview202402-Q5_0.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q5_0.gguf) | Q5_0 | 4.204 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [CantoneseLLM-6B-preview202402-Q5_K_S.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q5_K_S.gguf) | Q5_K_S | 4.204 GB | large, low quality loss - recommended |
+| [CantoneseLLM-6B-preview202402-Q5_K_M.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q5_K_M.gguf) | Q5_K_M | 4.304 GB | large, very low quality loss - recommended |
+| [CantoneseLLM-6B-preview202402-Q6_K.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q6_K.gguf) | Q6_K | 4.974 GB | very large, extremely low quality loss |
+| [CantoneseLLM-6B-preview202402-Q8_0.gguf](https://huggingface.co/tensorblock/CantoneseLLM-6B-preview202402-GGUF/blob/main/CantoneseLLM-6B-preview202402-Q8_0.gguf) | Q8_0 | 6.442 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/CantoneseLLM-6B-preview202402-GGUF --include "CantoneseLLM-6B-preview202402-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/CantoneseLLM-6B-preview202402-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```