Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,16 @@ 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
+moe-x33-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q8_0/moe-x33-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+moe-x33-Q8_0/moe-x33-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,189 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- code
+- moe
+- TensorBlock
+- GGUF
+datasets:
+- andersonbcdefg/synthetic_retrieval_tasks
+- ise-uiuc/Magicoder-Evol-Instruct-110K
+metrics:
+- code_eval
+base_model: senseable/moe-x33
+model-index:
+- name: moe-x33
+  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: 26.19
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 26.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 24.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 51.14
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 50.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=senseable/moe-x33
+      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>
+
+## senseable/moe-x33 - GGUF
+
+This repo contains GGUF format model files for [senseable/moe-x33](https://huggingface.co/senseable/moe-x33).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [moe-x33-Q2_K.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q2_K.gguf) | Q2_K | 21.625 GB | smallest, significant quality loss - not recommended for most purposes |
+| [moe-x33-Q3_K_S.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q3_K_S.gguf) | Q3_K_S | 25.425 GB | very small, high quality loss |
+| [moe-x33-Q3_K_M.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q3_K_M.gguf) | Q3_K_M | 28.280 GB | very small, high quality loss |
+| [moe-x33-Q3_K_L.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q3_K_L.gguf) | Q3_K_L | 30.763 GB | small, substantial quality loss |
+| [moe-x33-Q4_0.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q4_0.gguf) | Q4_0 | 33.222 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [moe-x33-Q4_K_S.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q4_K_S.gguf) | Q4_K_S | 33.466 GB | small, greater quality loss |
+| [moe-x33-Q4_K_M.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q4_K_M.gguf) | Q4_K_M | 35.408 GB | medium, balanced quality - recommended |
+| [moe-x33-Q5_0.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q5_0.gguf) | Q5_0 | 40.561 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [moe-x33-Q5_K_S.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q5_K_S.gguf) | Q5_K_S | 40.561 GB | large, low quality loss - recommended |
+| [moe-x33-Q5_K_M.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q5_K_M.gguf) | Q5_K_M | 41.687 GB | large, very low quality loss - recommended |
+| [moe-x33-Q6_K.gguf](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q6_K.gguf) | Q6_K | 48.358 GB | very large, extremely low quality loss |
+| [moe-x33-Q8_0](https://huggingface.co/tensorblock/moe-x33-GGUF/blob/main/moe-x33-Q8_0) | Q8_0 | 42.254 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/moe-x33-GGUF --include "moe-x33-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/moe-x33-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

moe-x33-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8172ac8a1df378cf6b9c3ed98c760ee9731c90cdb5bf068896cb3190b051c06f
+size 21625389952

moe-x33-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ad6b2ca5ede395c67345f9659b81136c54f9af40e42db87a33aca1166cc418
+size 30762955648

moe-x33-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a379634e76d98ba1937b21a60ff595b638d308b83ee87ca25e7b84288a056ad0
+size 28279731072

moe-x33-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01f4f0e92a5b488e0d96f3817653bcb067dd3bc436c62a7d09c65f22670e669
+size 25424630656

moe-x33-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e22d5ff7f047652360fa634c96854a6ba606480503b12e9e2f614cce8e7049c
+size 33221952384

moe-x33-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec1fd0721ee38e3f53435a602150aadd45076431052dc0931b70d18fbab340b
+size 35407618944

moe-x33-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53eeffc5bf7b13a26a522d1c53c42eab5d29bf7ac9ff96f24b960543e1d78e59
+size 33466467200

moe-x33-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d4eb7b170ad7b89c661dd2c94c83ea947c7dda2fdca29b55636554f27d28d8
+size 40560608128

moe-x33-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79009743bda65881450f51344cfddd9e56b5ab75b7dc78a65fd7c37d3569a481
+size 41686557568

moe-x33-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960fb08c4a66163c46993efe24479614ac2835e4767d53a5acebe23283770537
+size 40560608128

moe-x33-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4811be836dd8e11863255d6f057c90362e481438f25e50d7658be87acd3882ea
+size 48357929856

moe-x33-Q8_0/moe-x33-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85074ff8a96e6f5146beb0963532b53b191b1cdc9997c58534f4a7c47369f39e
+size 34986581728

moe-x33-Q8_0/moe-x33-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae227653d4164280774894dc7fdfb919175729b12ef586549655dfa55d361dc
+size 7267037184