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
+yi6B_Vicuna-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+yi6B_Vicuna-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,183 @@
+---
+language:
+- en
+license: mit
+datasets:
+- anon8231489123/ShareGPT_Vicuna_unfiltered
+base_model: lorinma/yi6B_Vicuna
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: yi6B_Vicuna
+  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: 46.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lorinma/yi6B_Vicuna
+      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: 69.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lorinma/yi6B_Vicuna
+      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: 58.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lorinma/yi6B_Vicuna
+      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: 48.11
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lorinma/yi6B_Vicuna
+      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: 65.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lorinma/yi6B_Vicuna
+      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: 18.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lorinma/yi6B_Vicuna
+      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>
+
+## lorinma/yi6B_Vicuna - GGUF
+
+This repo contains GGUF format model files for [lorinma/yi6B_Vicuna](https://huggingface.co/lorinma/yi6B_Vicuna).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [yi6B_Vicuna-Q2_K.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q2_K.gguf) | Q2_K | 2.337 GB | smallest, significant quality loss - not recommended for most purposes |
+| [yi6B_Vicuna-Q3_K_S.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q3_K_S.gguf) | Q3_K_S | 2.709 GB | very small, high quality loss |
+| [yi6B_Vicuna-Q3_K_M.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q3_K_M.gguf) | Q3_K_M | 2.993 GB | very small, high quality loss |
+| [yi6B_Vicuna-Q3_K_L.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q3_K_L.gguf) | Q3_K_L | 3.237 GB | small, substantial quality loss |
+| [yi6B_Vicuna-Q4_0.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q4_0.gguf) | Q4_0 | 3.479 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [yi6B_Vicuna-Q4_K_S.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q4_K_S.gguf) | Q4_K_S | 3.503 GB | small, greater quality loss |
+| [yi6B_Vicuna-Q4_K_M.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q4_K_M.gguf) | Q4_K_M | 3.674 GB | medium, balanced quality - recommended |
+| [yi6B_Vicuna-Q5_0.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q5_0.gguf) | Q5_0 | 4.204 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [yi6B_Vicuna-Q5_K_S.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q5_K_S.gguf) | Q5_K_S | 4.204 GB | large, low quality loss - recommended |
+| [yi6B_Vicuna-Q5_K_M.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q5_K_M.gguf) | Q5_K_M | 4.304 GB | large, very low quality loss - recommended |
+| [yi6B_Vicuna-Q6_K.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q6_K.gguf) | Q6_K | 4.974 GB | very large, extremely low quality loss |
+| [yi6B_Vicuna-Q8_0.gguf](https://huggingface.co/tensorblock/yi6B_Vicuna-GGUF/blob/main/yi6B_Vicuna-Q8_0.gguf) | Q8_0 | 6.442 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/yi6B_Vicuna-GGUF --include "yi6B_Vicuna-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/yi6B_Vicuna-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

yi6B_Vicuna-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebccd8370ab808fb26851474625e294c0d507c2693a301060434ae5db3c1345
+size 2337066880

yi6B_Vicuna-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc0e4e4365f9a68d2b03f1b08525abec1a6fc3958744ab4eca8e2b3beb5c108
+size 3236892544

yi6B_Vicuna-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59372b6a6b0004c8ef6630c47638f0092797e3cb4352ce71511d56fe4d5299ea
+size 2992836480

yi6B_Vicuna-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1e36375ec72716d4b50164275ca460d9ea4eb88dc73faa6890659a05d95a06
+size 2709196672

yi6B_Vicuna-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811a9c5f60bf342fcbaebf3d802148b753f6bdcb51a897aa4aa13f292d5bc942
+size 3479326592

yi6B_Vicuna-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d5b267a2a7bc33df68a7f6e88b59ca0251f2c907e8eaad1c4a61414799301a
+size 3673968512

yi6B_Vicuna-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0425808c5edde67d6ecf719cac387d77795cb13c0be1b7c4529205f5d52027e7
+size 3502919552

yi6B_Vicuna-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdd66da85a1a70da62206235c3a7152e5c82f65d5791877dd48d2131c027911
+size 4204154752

yi6B_Vicuna-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d5bdf868dac3dc7edccb47bdce8c7107381520563c373ff06132da5e8b395a
+size 4304424832

yi6B_Vicuna-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4861100f40c2e3b95b7b8ba1b7b2babd39d95c28d0beb8c9cc7b7d7a572755d1
+size 4204154752

yi6B_Vicuna-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b301fa8cefb616ee53ee22c2ae301631e2d5633e0ded99ae708b75826e71ae9d
+size 4974284672

yi6B_Vicuna-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ce966541320ee1b325c140db16236485f7b0c625d1ad2abe39e753574388b7
+size 6442127232