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
+zephyr-7b-beta-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-beta-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,238 @@
+---
+tags:
+- generated_from_trainer
+- TensorBlock
+- GGUF
+license: mit
+datasets:
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+language:
+- en
+base_model: HuggingFaceH4/zephyr-7b-beta
+widget:
+- example_title: Pirate!
+  messages:
+  - role: system
+    content: You are a pirate chatbot who always responds with Arr!
+  - role: user
+    content: There's a llama on my lawn, how can I get rid of him?
+  output:
+    text: Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare sight,
+      but I've got a plan that might help ye get rid of 'im. Ye'll need to gather
+      some carrots and hay, and then lure the llama away with the promise of a tasty
+      treat. Once he's gone, ye can clean up yer lawn and enjoy the peace and quiet
+      once again. But beware, me hearty, for there may be more llamas where that one
+      came from! Arr!
+pipeline_tag: text-generation
+model-index:
+- name: zephyr-7b-beta
+  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: 62.03071672354948
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      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: 84.35570603465445
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Drop (3-Shot)
+      type: drop
+      split: validation
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: f1
+      value: 9.66243708053691
+      name: f1 score
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      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: 57.44916942762855
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      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: 12.736921910538287
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      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: 61.07
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      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: 77.7426992896606
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AlpacaEval
+      type: tatsu-lab/alpaca_eval
+    metrics:
+    - type: unknown
+      value: 0.906
+      name: win rate
+    source:
+      url: https://tatsu-lab.github.io/alpaca_eval/
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MT-Bench
+      type: unknown
+    metrics:
+    - type: unknown
+      value: 7.34
+      name: score
+    source:
+      url: https://huggingface.co/spaces/lmsys/mt-bench
+---
+
+<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>
+
+## HuggingFaceH4/zephyr-7b-beta - GGUF
+
+This repo contains GGUF format model files for [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta).
+
+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).
+
+## Prompt template
+
+```
+<|system|>
+{system_prompt}</s>
+<|user|>
+{prompt}</s>
+<|assistant|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [zephyr-7b-beta-Q2_K.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [zephyr-7b-beta-Q3_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [zephyr-7b-beta-Q3_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [zephyr-7b-beta-Q3_K_L.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [zephyr-7b-beta-Q4_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [zephyr-7b-beta-Q4_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [zephyr-7b-beta-Q4_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [zephyr-7b-beta-Q5_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [zephyr-7b-beta-Q5_K_S.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [zephyr-7b-beta-Q5_K_M.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [zephyr-7b-beta-Q6_K.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [zephyr-7b-beta-Q8_0.gguf](https://huggingface.co/tensorblock/zephyr-7b-beta-GGUF/tree/main/zephyr-7b-beta-Q8_0.gguf) | Q8_0 | 7.167 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/zephyr-7b-beta-GGUF --include "zephyr-7b-beta-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/zephyr-7b-beta-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

zephyr-7b-beta-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5a1dca3543a5487c0de63a377d9614e68b2bc2e4df87bc422db752b6bcfc52
+size 2719243264

zephyr-7b-beta-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32433d71d0b423eada1626608a7ed7a7e0be4bfc2790578276fde59e8804489a
+size 3822025728

zephyr-7b-beta-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6519295258361da96da2e51f8e4733301e5ca26cdd15876b01350a88d6072a
+size 3518987264

zephyr-7b-beta-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8f38905cf4665c5e3fcbff7a94c419ddd6437d56a3c7eda069a8a648adb616
+size 3164568576

zephyr-7b-beta-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9895a27bbc4a0ec3b7adfe17cd90c85a12bbfb245677004258ecae6e13d33b
+size 4108917760

zephyr-7b-beta-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ecd7186ec22b778831dc274db95755d2feaa63cf44289ec3aa60d81729d1a2
+size 4368440320

zephyr-7b-beta-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d44a6b89eb341e09d2ecc13fd6f9d009e275f3546ce3a95110f0decdb648747
+size 4140375040

zephyr-7b-beta-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6fd69af5b0f834dc02bd5591f7d21ca98f01abc8fcc0985a5fb6de75039eb7
+size 4997716992

zephyr-7b-beta-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d437bea0ff62e2565529813441cdf56353d7f6d2392bdf9eba6a87a4bfbed3
+size 5131410432

zephyr-7b-beta-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8146e47e3b24f56d926548898d1853360a0a61780d56c307d7ca39bdf5c29578
+size 4997716992

zephyr-7b-beta-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9416265d60c7f69d139a660cf3ba26009492fb818162c1f193be6c3150d6c7ab
+size 5942066176

zephyr-7b-beta-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa693a2fb69d7587b0c664a0e7d0f7fdc18eb0bb3ff4acec57add63a782c273
+size 7695858688