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-200k-Q-FastChat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+PlatYi-34B-200k-Q-FastChat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

PlatYi-34B-200k-Q-FastChat-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c279bdd29d4582af4f5c6c8b0c0c5875e78c34fe5400cfe7b8ed4024db04bb91
+size 12825234080

PlatYi-34B-200k-Q-FastChat-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a6fec6ddca534c0e2bad443f9c87eed7d5b7b45870feead894231cbcd16e5e
+size 18139445920

PlatYi-34B-200k-Q-FastChat-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07343de0b4edf1d99c873e74a545f05b902cc31f92d0a11980f653e207d22767
+size 16654924448

PlatYi-34B-200k-Q-FastChat-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72dfd1e0fbee659c6c498edc1f2e68c545c870b8980a7dc21a89036a8d3b96a
+size 14960294560

PlatYi-34B-200k-Q-FastChat-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60730d6e04450cbf854529cabd46f4395832da53ebb2eb8b7d74752ae9e7c60f
+size 19466529440

PlatYi-34B-200k-Q-FastChat-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3560aa564d22fcd2e558731752c0198f5026388398d3f2921e7c39c493f102
+size 20658711200

PlatYi-34B-200k-Q-FastChat-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3127c7e9b33b800a9cb8b8aec2e304800d5aae863867831e457556ece68f451
+size 19598650016

PlatYi-34B-200k-Q-FastChat-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac117172fd96d0d65963ec8974407e66613145bf17dd8d05aec3b453996876a
+size 23707691680

PlatYi-34B-200k-Q-FastChat-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373ed7c84caaeefd0791c774944d2fd27539e60acb7cf1641f2c5db41279d48
+size 24321845920

PlatYi-34B-200k-Q-FastChat-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506785823ebe7edba95603a33e62039069508be4c3acc015db99cb15e3760d60
+size 23707691680

PlatYi-34B-200k-Q-FastChat-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0dff7ae451bbd7b9e0952c749e3b929f3b4f539a926d61fe939547baf87ef0e
+size 28213926560

PlatYi-34B-200k-Q-FastChat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0064aa5ffef1c35fa9440814b9973ebadc29c41156b312c43bc1996eb0debb46
+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-200k-Q-FastChat
+model-index:
+- name: PlatYi-34B-200k-Q-FastChat
+  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: 64.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat
+      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: 84.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat
+      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: 77.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat
+      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: 48.38
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat
+      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: 80.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat
+      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: 51.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat
+      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-200k-Q-FastChat - GGUF
+
+This repo contains GGUF format model files for [kyujinpy/PlatYi-34B-200k-Q-FastChat](https://huggingface.co/kyujinpy/PlatYi-34B-200k-Q-FastChat).
+
+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-200k-Q-FastChat-Q2_K.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q2_K.gguf) | Q2_K | 12.825 GB | smallest, significant quality loss - not recommended for most purposes |
+| [PlatYi-34B-200k-Q-FastChat-Q3_K_S.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q3_K_S.gguf) | Q3_K_S | 14.960 GB | very small, high quality loss |
+| [PlatYi-34B-200k-Q-FastChat-Q3_K_M.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q3_K_M.gguf) | Q3_K_M | 16.655 GB | very small, high quality loss |
+| [PlatYi-34B-200k-Q-FastChat-Q3_K_L.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q3_K_L.gguf) | Q3_K_L | 18.139 GB | small, substantial quality loss |
+| [PlatYi-34B-200k-Q-FastChat-Q4_0.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q4_0.gguf) | Q4_0 | 19.467 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [PlatYi-34B-200k-Q-FastChat-Q4_K_S.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q4_K_S.gguf) | Q4_K_S | 19.599 GB | small, greater quality loss |
+| [PlatYi-34B-200k-Q-FastChat-Q4_K_M.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q4_K_M.gguf) | Q4_K_M | 20.659 GB | medium, balanced quality - recommended |
+| [PlatYi-34B-200k-Q-FastChat-Q5_0.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q5_0.gguf) | Q5_0 | 23.708 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [PlatYi-34B-200k-Q-FastChat-Q5_K_S.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q5_K_S.gguf) | Q5_K_S | 23.708 GB | large, low quality loss - recommended |
+| [PlatYi-34B-200k-Q-FastChat-Q5_K_M.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q5_K_M.gguf) | Q5_K_M | 24.322 GB | large, very low quality loss - recommended |
+| [PlatYi-34B-200k-Q-FastChat-Q6_K.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-Q6_K.gguf) | Q6_K | 28.214 GB | very large, extremely low quality loss |
+| [PlatYi-34B-200k-Q-FastChat-Q8_0.gguf](https://huggingface.co/tensorblock/PlatYi-34B-200k-Q-FastChat-GGUF/blob/main/PlatYi-34B-200k-Q-FastChat-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-200k-Q-FastChat-GGUF --include "PlatYi-34B-200k-Q-FastChat-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-200k-Q-FastChat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```