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
+PlatYi-34B-Llama-Q-v3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-Llama-Q-v3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

PlatYi-34B-Llama-Q-v3-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858be568b63383b9c7931b82e231a085714232afb4c4e95b729a93d35401d74b
+size 12825234080

PlatYi-34B-Llama-Q-v3-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0af400a5200619596cd3f5aa6262cd87b8dbe559eeb1ecd467604eb057aef5b
+size 18139445920

PlatYi-34B-Llama-Q-v3-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0add154147c87b9438f5f2e77a1796a367c8e3476fc419fb5c4be5983fbc1ae3
+size 16654924448

PlatYi-34B-Llama-Q-v3-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1af9ef981174449422855d01ad1c804f968b940cf3f5f639c50cede1d60c11
+size 14960294560

PlatYi-34B-Llama-Q-v3-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51224c7a554d6d581aa5f0d0f9ebb31cbc658dbf1d671633207da0ea6fea9e4b
+size 19466529440

PlatYi-34B-Llama-Q-v3-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cb353a34f9d638734943ca01521183f0eaf84762e335dd0ab35f590773da23
+size 20658711200

PlatYi-34B-Llama-Q-v3-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fc08f9d3bb548dfafadc99590525edbf406d3f457cd61cd0ba40e0991c4b13
+size 19598650016

PlatYi-34B-Llama-Q-v3-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee5253860497e77e68866832960c494e1a6aee32fb05cbaf67d2ccc185eb920
+size 23707691680

PlatYi-34B-Llama-Q-v3-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f79324ec8383d62b78827704b9824e2029224fd9c9de08cd526e087a9e0f1c
+size 24321845920

PlatYi-34B-Llama-Q-v3-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d327a9bd9052a4c752ba2d06e1b398a29acc99ca111eaa3a397b425a063155ce
+size 23707691680

PlatYi-34B-Llama-Q-v3-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b69047eaf11e04ca4a1a919bb52a19f677ca6c65b5105534f16d4d997e8f6f
+size 28213926560

PlatYi-34B-Llama-Q-v3-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77945e54bbb3eb0cbea227f928e49f7aec7f723823de2eaae4417b8a954bf9d4
+size 36542282400

README.md

@@ -0,0 +1,185 @@
+---
+language:
+- en
+license: cc-by-nc-sa-4.0
+library_name: transformers
+datasets:
+- garage-bAInd/Open-Platypus
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: kyujinpy/PlatYi-34B-Llama-Q-v3
+model-index:
+- name: PlatYi-34B-Llama-Q-v3
+  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: 64.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v3
+      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: 84.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v3
+      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: 74.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v3
+      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: 51.8
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v3
+      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: 84.21
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v3
+      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: 6.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v3
+      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>
+
+## kyujinpy/PlatYi-34B-Llama-Q-v3 - GGUF
+
+This repo contains GGUF format model files for [kyujinpy/PlatYi-34B-Llama-Q-v3](https://huggingface.co/kyujinpy/PlatYi-34B-Llama-Q-v3).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [PlatYi-34B-Llama-Q-v3-Q2_K.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q2_K.gguf) | Q2_K | 12.825 GB | smallest, significant quality loss - not recommended for most purposes |
+| [PlatYi-34B-Llama-Q-v3-Q3_K_S.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q3_K_S.gguf) | Q3_K_S | 14.960 GB | very small, high quality loss |
+| [PlatYi-34B-Llama-Q-v3-Q3_K_M.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q3_K_M.gguf) | Q3_K_M | 16.655 GB | very small, high quality loss |
+| [PlatYi-34B-Llama-Q-v3-Q3_K_L.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q3_K_L.gguf) | Q3_K_L | 18.139 GB | small, substantial quality loss |
+| [PlatYi-34B-Llama-Q-v3-Q4_0.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q4_0.gguf) | Q4_0 | 19.467 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [PlatYi-34B-Llama-Q-v3-Q4_K_S.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q4_K_S.gguf) | Q4_K_S | 19.599 GB | small, greater quality loss |
+| [PlatYi-34B-Llama-Q-v3-Q4_K_M.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q4_K_M.gguf) | Q4_K_M | 20.659 GB | medium, balanced quality - recommended |
+| [PlatYi-34B-Llama-Q-v3-Q5_0.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q5_0.gguf) | Q5_0 | 23.708 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [PlatYi-34B-Llama-Q-v3-Q5_K_S.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q5_K_S.gguf) | Q5_K_S | 23.708 GB | large, low quality loss - recommended |
+| [PlatYi-34B-Llama-Q-v3-Q5_K_M.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q5_K_M.gguf) | Q5_K_M | 24.322 GB | large, very low quality loss - recommended |
+| [PlatYi-34B-Llama-Q-v3-Q6_K.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q6_K.gguf) | Q6_K | 28.214 GB | very large, extremely low quality loss |
+| [PlatYi-34B-Llama-Q-v3-Q8_0.gguf](https://huggingface.co/tensorblock/PlatYi-34B-Llama-Q-v3-GGUF/blob/main/PlatYi-34B-Llama-Q-v3-Q8_0.gguf) | Q8_0 | 36.542 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/PlatYi-34B-Llama-Q-v3-GGUF --include "PlatYi-34B-Llama-Q-v3-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/PlatYi-34B-Llama-Q-v3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```