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
+Sailor-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Sailor-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,216 @@
+---
+language:
+- en
+- zh
+- id
+- th
+- vi
+- ms
+- lo
+datasets:
+- cerebras/SlimPajama-627B
+- Skywork/SkyPile-150B
+- allenai/MADLAD-400
+- cc100
+tags:
+- multilingual
+- sea
+- sailor
+- TensorBlock
+- GGUF
+license: apache-2.0
+base_model: sail/Sailor-7B
+model-index:
+- name: Sailor-7B
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD-Thai
+      type: XQuAD-Thai
+    metrics:
+    - type: EM (3-Shot)
+      value: 57.88
+      name: EM (3-Shot)
+    - type: F1 (3-Shot)
+      value: 71.06
+      name: F1 (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: TyDiQA-Indonesian
+      type: TyDiQA-Indonesian
+    metrics:
+    - type: EM (3-Shot)
+      value: 60.53
+      name: EM (3-Shot)
+    - type: F1 (3-Shot)
+      value: 75.42
+      name: F1 (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD-Vietnamese
+      type: XQuAD-Vietnamese
+    metrics:
+    - type: EM (3-Shot)
+      value: 53.81
+      name: EM (3-Shot)
+    - type: F1 (3-Shot)
+      value: 74.62
+      name: F1 (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: XCOPA-Thai
+      type: XCOPA-Thai
+    metrics:
+    - type: EM (3-Shot)
+      value: 59.0
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: XCOPA-Indonesian
+      type: XCOPA-Indonesian
+    metrics:
+    - type: EM (3-Shot)
+      value: 72.2
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: XCOPA-Vietnamese
+      type: XCOPA-Vietnamese
+    metrics:
+    - type: EM (3-Shot)
+      value: 72.2
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: M3Exam-Thai
+      type: M3Exam-Thai
+    metrics:
+    - type: EM (3-Shot)
+      value: 30.0
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: M3Exam-Indonesian
+      type: M3Exam-Indonesian
+    metrics:
+    - type: EM (3-Shot)
+      value: 32.88
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: M3Exam-Vietnamese
+      type: M3Exam-Vietnamese
+    metrics:
+    - type: EM (3-Shot)
+      value: 44.1
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: BELEBELE-Thai
+      type: BELEBELE-Thai
+    metrics:
+    - type: EM (3-Shot)
+      value: 41.56
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: BELEBELE-Indonesian
+      type: BELEBELE-Indonesian
+    metrics:
+    - type: EM (3-Shot)
+      value: 44.33
+      name: EM (3-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: BELEBELE-Vietnamese
+      type: BELEBELE-Vietnamese
+    metrics:
+    - type: EM (3-Shot)
+      value: 45.33
+      name: EM (3-Shot)
+---
+
+<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>
+
+## sail/Sailor-7B - GGUF
+
+This repo contains GGUF format model files for [sail/Sailor-7B](https://huggingface.co/sail/Sailor-7B).
+
+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
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Sailor-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q2_K.gguf) | Q2_K | 3.104 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Sailor-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q3_K_S.gguf) | Q3_K_S | 3.569 GB | very small, high quality loss |
+| [Sailor-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q3_K_M.gguf) | Q3_K_M | 3.919 GB | very small, high quality loss |
+| [Sailor-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q3_K_L.gguf) | Q3_K_L | 4.218 GB | small, substantial quality loss |
+| [Sailor-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q4_0.gguf) | Q4_0 | 4.512 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Sailor-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q4_K_S.gguf) | Q4_K_S | 4.543 GB | small, greater quality loss |
+| [Sailor-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q4_K_M.gguf) | Q4_K_M | 4.767 GB | medium, balanced quality - recommended |
+| [Sailor-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q5_0.gguf) | Q5_0 | 5.399 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Sailor-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q5_K_S.gguf) | Q5_K_S | 5.399 GB | large, low quality loss - recommended |
+| [Sailor-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q5_K_M.gguf) | Q5_K_M | 5.531 GB | large, very low quality loss - recommended |
+| [Sailor-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q6_K.gguf) | Q6_K | 6.342 GB | very large, extremely low quality loss |
+| [Sailor-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Sailor-7B-GGUF/blob/main/Sailor-7B-Q8_0.gguf) | Q8_0 | 8.212 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/Sailor-7B-GGUF --include "Sailor-7B-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/Sailor-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Sailor-7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915ed31e5d43dfe29b8e3f3eb6055000141b1785167f24bbb0b845eef4da9688
+size 3103826432

Sailor-7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4876d1859d5c5a19814f8db1084e72eac6f9c1256c020d392c4f1f2aeb5bc95
+size 4217967104

Sailor-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aff10fda5b314017199bf4a699a4093b89b05ea50134cc266c28bed060a3d3b
+size 3918860800

Sailor-7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79df606d0fd8f6f6b8105bd7f30094cfd3b3124f4709662edbd5ec0a261c8fb
+size 3569160704

Sailor-7B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27b03babe739cfcaecae8980e62d16443317f607f054ea8c8fe75a4c9954fa2
+size 4511908352

Sailor-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1337ff48a21434c6e6e2cbabb24406a5c0d9c3b9d175ad981741467e15a74f1f
+size 4767105536

Sailor-7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e374d5e17e0708b16967e34dee2d4bc1b3f0a3dbaaebc8ded3d666225c5446ca
+size 4542841344

Sailor-7B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9130b026bc52d5cdfe53f1ccd9f7a59394c6afa1d14260172dcadbf242ad9fe
+size 5399200256

Sailor-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142df9b4faaf6981405578ab1c3710572dd74be183ef3272f5c4334827892bad
+size 5530665472

Sailor-7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad00d2b990fd572827dd4c6d9c841b5d5f026fadb44498c5c303bd697e189ac1
+size 5399200256

Sailor-7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1caaa1eff39c955e96f3ffd92cd291e36e6d74270f27518469cc15997ad0d6
+size 6341947904

Sailor-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b212976638cd4909ff6b674f2fa82490a84eed35572cc39a73c3d53067471fd
+size 8211796480