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-3-8B-Instruct-v0.10-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.10-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-Instruct-v0.10-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129ad59b754706d7d4fe930ff2b489fabd7351c69fec616a4a4341ef3ff4a737
+size 3179132288

Llama-3-8B-Instruct-v0.10-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14434b5276eb479756eacecd780290b723c0e8b6b2a13b781e57538d9bf3317
+size 4321957248

Llama-3-8B-Instruct-v0.10-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac61b3b972000de489585e4c0d9fce843ebd8c62c2c28c235bbeaa9c0afa9675
+size 4018918784

Llama-3-8B-Instruct-v0.10-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157e215ef43b1de1ccf23546fa7d45f04bbe76839c5553a03af467939e03406a
+size 3664500096

Llama-3-8B-Instruct-v0.10-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0d348424e6d04687b3d685f87e8fa7b6784288a2d3e3e3321cce6c4db0aea0
+size 4661212544

Llama-3-8B-Instruct-v0.10-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045207d8cab074151c791da8996ee5513d44125b6432fbe6b557aafb7ef4f464
+size 4920735104

Llama-3-8B-Instruct-v0.10-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef364271488aeb234061e0d62fe44d7b469ab3a71969dafbb366c49558f90b4c
+size 4692669824

Llama-3-8B-Instruct-v0.10-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134b7d0ea06f9495636befe626ce5631542d3de86a092356a702f8dc4fd58baa
+size 5599294848

Llama-3-8B-Instruct-v0.10-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7dbbdc104c5ca6d0729eb4f910f9bd2df38a26347b2823c8252b6999b20c5a
+size 5732988288

Llama-3-8B-Instruct-v0.10-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc831c82c64b5d9f350758bc95eed4c27d61bf6331b518640931ac6ea2f0d766
+size 5599294848

Llama-3-8B-Instruct-v0.10-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa086b0e14850e701534169e0afd6755ba3b5b3fe550d4f0c2f590db2a8f110
+size 6596007296

Llama-3-8B-Instruct-v0.10-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68cb539bc811c08be523eb2c396de87ebd9297e9cc44fc6d2186073d0cba7ae
+size 8540771712

README.md

@@ -0,0 +1,184 @@
+---
+language:
+- en
+license: other
+library_name: transformers
+tags:
+- axolotl
+- finetune
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+- TensorBlock
+- GGUF
+base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+pipeline_tag: text-generation
+license_name: llama3
+license_link: LICENSE
+inference: false
+model_creator: MaziyarPanahi
+model-index:
+- name: Llama-3-8B-Instruct-v0.10
+  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: 76.67
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+      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: 27.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+      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: 4.91
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+      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: 7.83
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+      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: 10.81
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+      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: 31.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
+      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>
+
+## MaziyarPanahi/Llama-3-8B-Instruct-v0.10 - GGUF
+
+This repo contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-v0.10](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.10).
+
+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|>
+
+{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-3-8B-Instruct-v0.10-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-8B-Instruct-v0.10-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [Llama-3-8B-Instruct-v0.10-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [Llama-3-8B-Instruct-v0.10-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [Llama-3-8B-Instruct-v0.10-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-8B-Instruct-v0.10-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [Llama-3-8B-Instruct-v0.10-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [Llama-3-8B-Instruct-v0.10-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-8B-Instruct-v0.10-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [Llama-3-8B-Instruct-v0.10-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [Llama-3-8B-Instruct-v0.10-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [Llama-3-8B-Instruct-v0.10-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.10-GGUF/tree/main/Llama-3-8B-Instruct-v0.10-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-3-8B-Instruct-v0.10-GGUF --include "Llama-3-8B-Instruct-v0.10-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-3-8B-Instruct-v0.10-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```