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
+Llama-3.1-8B-Ultra-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Ultra-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.1-8B-Ultra-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af55804c7d19a4607617fc539cffc1aaa697206cd25ea6603a1df8fc8b69a222
+size 3179137216

Llama-3.1-8B-Ultra-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46803dfddc24c8aa47d387ff7192bbeb05b6f0ff9793ed159710b5eeaac00531
+size 4321962176

Llama-3.1-8B-Ultra-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6768099e45198ed7b9bd1ddad29adca378ce962a302b7a544702f12b59b6fd
+size 4018923712

Llama-3.1-8B-Ultra-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125b7ea0e3b2e81fd89787fb9525a502f88ee88a58336147c08c582adfe1c59d
+size 3664505024

Llama-3.1-8B-Ultra-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c8ac7701a4ca00a241391fdd6d992740687271e3358788c612b6411f1bb0d4
+size 4661217472

Llama-3.1-8B-Ultra-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2114176243a5b5e8efd1451c950efd30bd9d639e4b59eb8eb8faa4d738351d8f
+size 4920740032

Llama-3.1-8B-Ultra-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be93892c1ff1b4d305979a15c23eff43fe95175ce2d097b825d018b4cec5563d
+size 4692674752

Llama-3.1-8B-Ultra-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bcead8bede072aea2a56b668665c672f74df1da807a3e63a03dd5a1304b177
+size 5599299776

Llama-3.1-8B-Ultra-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7c747ffcbb3808351f33592130156647ba298d3b7ddab1b6575ce31c3e548e
+size 5732993216

Llama-3.1-8B-Ultra-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e6649095363ed8f679dfb33103c73693022d29d6e410768737bec4169a40e9
+size 5599299776

Llama-3.1-8B-Ultra-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c9b66ee8ca2daee9427e9734433698835716f735ca8e3f6782f2540a2ceca7
+size 6596012224

Llama-3.1-8B-Ultra-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bba64d8e94ab997908bcad03428ca2a30da70f8912448fd9c7af894811d06e
+size 8540776640

README.md

@@ -0,0 +1,175 @@
+---
+license: llama3
+library_name: transformers
+tags:
+- mergekit
+- merge
+- TensorBlock
+- GGUF
+base_model: Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+model-index:
+- name: Llama-3.1-8B-Ultra-Instruct
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 80.81
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 32.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 14.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 8.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 31.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dampfinchen/Llama-3.1-8B-Ultra-Instruct
+      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>
+
+## Dampfinchen/Llama-3.1-8B-Ultra-Instruct - GGUF
+
+This repo contains GGUF format model files for [Dampfinchen/Llama-3.1-8B-Ultra-Instruct](https://huggingface.co/Dampfinchen/Llama-3.1-8B-Ultra-Instruct).
+
+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
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+Cutting Knowledge Date: December 2023
+Today Date: 26 Jul 2024
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Llama-3.1-8B-Ultra-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.1-8B-Ultra-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [Llama-3.1-8B-Ultra-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [Llama-3.1-8B-Ultra-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [Llama-3.1-8B-Ultra-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.1-8B-Ultra-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [Llama-3.1-8B-Ultra-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [Llama-3.1-8B-Ultra-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.1-8B-Ultra-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [Llama-3.1-8B-Ultra-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [Llama-3.1-8B-Ultra-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [Llama-3.1-8B-Ultra-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF/tree/main/Llama-3.1-8B-Ultra-Instruct-Q8_0.gguf) | Q8_0 | 7.954 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/Llama-3.1-8B-Ultra-Instruct-GGUF --include "Llama-3.1-8B-Ultra-Instruct-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/Llama-3.1-8B-Ultra-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```