Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ 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
+Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K/Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K/Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc26fa3ddf214d13981b9f0ab98b9085fd135b223fa19f8089a53ad88f1c2084
+size 26375108480

Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9588b5a5a724e5663691d7ffaf4696280aa17b0f4dd603d3c20e67ccaaa809
+size 37140592512

Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23741f85dd7d84844a9277e99b27b6f51f1aa79201537abf97580a618db2287a
+size 34267494272

Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca0244bc663f1eaf15780316237646c756e04c68918aa44cdb7759606a23dcb
+size 30912051072

Llama-3-70B-japanese-suzume-vector-v0.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14585255f72f808ccade6fcaed60f7b92d972b8e0aceedf6cc67dec00e226f91
+size 39969732480

Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5995184836156d9fc456443078dac1eb4f84a1eae6211fd953f474147e010f
+size 42520393600

Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8739cbfa36af3dfa70709241ea9f431a4194fb32840fae1a174a5eff18a23b5f
+size 40347219840

Llama-3-70B-japanese-suzume-vector-v0.1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc2da7b69946720939f0de631eeab4e50c7dd4d6719428af1bc8ec21a6aa720
+size 48657446784

Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa19259ebb2ae94b0042c787079c4f401cfb4b72991439d9282231517a0324c2
+size 49949816704

Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e540498f895a60c5a2b4fdf6fb247af9cd3b210df6660ecc305fea804605da1f
+size 48657446784

Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K/Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a061a3ba44cb28c91eff9d5e16fce7dfc14975e620d256a3b5b93cc685f824
+size 34847470496

Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K/Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb909ecd237ee7fc4e691f9a277459a86bdf72abe3c6f4da0fe8776787f64041
+size 23040672928

Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c97f9702ac795a3b81afa4a555655773c0c3b5c0b39fe133164404c3f0b8e4
+size 34980010976

Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8897b99174d98e7a0fba6dff98e7c326e07be8589e06abf61a123b7e608b5e
+size 34949976384

Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e65c99415273ddc702b437953b4d351cae1d51574637c9fc73fee0e5f3e06a
+size 5045062560

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+tags:
+- llama3
+- TensorBlock
+- GGUF
+license: llama3
+language:
+- ja
+- en
+base_model: mmnga/Llama-3-70B-japanese-suzume-vector-v0.1
+---
+
+<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>
+
+## mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 - GGUF
+
+This repo contains GGUF format model files for [mmnga/Llama-3-70B-japanese-suzume-vector-v0.1](https://huggingface.co/mmnga/Llama-3-70B-japanese-suzume-vector-v0.1).
+
+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
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
+| [Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0](https://huggingface.co/tensorblock/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/blob/main/Llama-3-70B-japanese-suzume-vector-v0.1-Q8_0) | Q8_0 | 74.975 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/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF --include "Llama-3-70B-japanese-suzume-vector-v0.1-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/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```