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
+suzume-llama-3-8B-japanese-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-japanese-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,86 @@
+---
+license: other
+license_name: llama-3
+license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/raw/main/LICENSE
+base_model: lightblue/suzume-llama-3-8B-japanese
+tags:
+- generated_from_trainer
+- TensorBlock
+- GGUF
+model-index:
+- name: workspace/llm_training/axolotl/llama3-ja/output_openchat_megagon_lbgpt4_ja_8B_instruct
+  results: []
+---
+
+<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>
+
+## lightblue/suzume-llama-3-8B-japanese - GGUF
+
+This repo contains GGUF format model files for [lightblue/suzume-llama-3-8B-japanese](https://huggingface.co/lightblue/suzume-llama-3-8B-japanese).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](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 |
+| -------- | ---------- | --------- | ----------- |
+| [suzume-llama-3-8B-japanese-Q2_K.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [suzume-llama-3-8B-japanese-Q3_K_S.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [suzume-llama-3-8B-japanese-Q3_K_M.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [suzume-llama-3-8B-japanese-Q3_K_L.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [suzume-llama-3-8B-japanese-Q4_0.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [suzume-llama-3-8B-japanese-Q4_K_S.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [suzume-llama-3-8B-japanese-Q4_K_M.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [suzume-llama-3-8B-japanese-Q5_0.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [suzume-llama-3-8B-japanese-Q5_K_S.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [suzume-llama-3-8B-japanese-Q5_K_M.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [suzume-llama-3-8B-japanese-Q6_K.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [suzume-llama-3-8B-japanese-Q8_0.gguf](https://huggingface.co/tensorblock/suzume-llama-3-8B-japanese-GGUF/blob/main/suzume-llama-3-8B-japanese-Q8_0.gguf) | Q8_0 | 7.954 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/suzume-llama-3-8B-japanese-GGUF --include "suzume-llama-3-8B-japanese-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/suzume-llama-3-8B-japanese-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

suzume-llama-3-8B-japanese-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88135dbeca98ba6597a040619f166fafb50431b2aa0506b4693abf2b1ec3890d
+size 3179131968

suzume-llama-3-8B-japanese-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6857517b33e814a1c32414366daafcaae109d0635d5ee0f850f3e496c47bf6db
+size 4321956928

suzume-llama-3-8B-japanese-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b025c1b33092286b2d7ed86c481ffe54eb86d29ec23819803f7b413cf594a5
+size 4018918464

suzume-llama-3-8B-japanese-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5010afe9d1f94ac6f0c35b650219fa0aba101bdec3fa919dd7735c74d79e1f5f
+size 3664499776

suzume-llama-3-8B-japanese-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9377ffd7e834c573134c91576de911038f6adde3da800a7928719ad745726c
+size 4661212224

suzume-llama-3-8B-japanese-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c78a04b9d122d45b8440a63643b4ea15dcc976969b7650e7e298f32ae17340e
+size 4920734784

suzume-llama-3-8B-japanese-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d090e2cf3d4e257da6d53e0d43e5ce1adeea5f55fa1e2be176bb53afe1830ab2
+size 4692669504

suzume-llama-3-8B-japanese-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35824c6e6426337c15b863655dc30aafa9f97637882aa16a465c3d32196d8603
+size 5599294528

suzume-llama-3-8B-japanese-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1252067db6ac5e3915a5b3a1e4a04db2923e58ceb854f27ebcf89c855677133
+size 5732987968

suzume-llama-3-8B-japanese-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2689ea569c68f47cce29617552e22a085db3981b4d42c98ac17a2135200905c2
+size 5599294528

suzume-llama-3-8B-japanese-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a4fba7142eac2d4cca91d1f4ae10af4b71c854b19986d064e61bf9d48fffb7
+size 6596006976

suzume-llama-3-8B-japanese-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bec20d5605d85612d888b2553e750500150cc5e6174b18eea01f7bee04a650e
+size 8540771392