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-v0.9-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-v0.9-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-Instruct-v0.9-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a73e8445e77a54141d8a2e83afb91fe4ca9bbe4992688d997632bb7e168f84
+size 3179132288

Llama-3-8B-Instruct-v0.9-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7329666e4b4751bbcefe03ba01fa80559d0ceb74b08ee9f0a6ca54906e75969
+size 4321957248

Llama-3-8B-Instruct-v0.9-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1300dcccd629e5b98c85d73a40856549919d178468afb37060004edcb71e8d4f
+size 4018918784

Llama-3-8B-Instruct-v0.9-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f047e28e278578600a94f47fe6218b515ca3616f12201cd978bece5a209091
+size 3664500096

Llama-3-8B-Instruct-v0.9-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2000ff2aaaf41bac93955a8b3803bb129d2f86f237cce100713d469fda388885
+size 4661212544

Llama-3-8B-Instruct-v0.9-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6bb745f67cb0957598df261f9b683cbc70a9047f5a9f9bdffe9b748e3e0438
+size 4920735104

Llama-3-8B-Instruct-v0.9-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9879f70ed7b637675f244390e72b39cd30b38abac32f06bb1470dd4b127a6edb
+size 4692669824

Llama-3-8B-Instruct-v0.9-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99adff6f6f958e841821f07bde3d8473a1465a7d547ae560d77be3549d36ef1
+size 5599294848

Llama-3-8B-Instruct-v0.9-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90715ada1bddddf41018d639e801f4b307f81747dc5a2f080d171d6d41609239
+size 5732988288

Llama-3-8B-Instruct-v0.9-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d462b788666d06b1351f7b60472c63ee10d24ff5889cf03e96b75b4a227ba85
+size 5599294848

Llama-3-8B-Instruct-v0.9-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ffcb0ad2a8d7c1e5f89e46b9f0b2fefbfeb7bfc350b0825e08a5522de9a42c
+size 6596007296

Llama-3-8B-Instruct-v0.9-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9509d260511fcc98d0d80da2569bb3defc7d641af97717d877d26f847d5c17b4
+size 8540771712

README.md

@@ -0,0 +1,193 @@
+---
+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-v0.9
+pipeline_tag: text-generation
+license_name: llama3
+license_link: LICENSE
+inference: false
+model_creator: MaziyarPanahi
+quantized_by: MaziyarPanahi
+model-index:
+- name: Llama-3-8B-Instruct-v0.9
+  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: 72.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 88.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 68.1
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 64.67
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 79.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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: 66.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.9
+      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-v0.9 - GGUF
+
+This repo contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-v0.9](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.9).
+
+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-v0.9-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-8B-Instruct-v0.9-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [Llama-3-8B-Instruct-v0.9-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [Llama-3-8B-Instruct-v0.9-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [Llama-3-8B-Instruct-v0.9-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-8B-Instruct-v0.9-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [Llama-3-8B-Instruct-v0.9-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [Llama-3-8B-Instruct-v0.9-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-8B-Instruct-v0.9-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [Llama-3-8B-Instruct-v0.9-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [Llama-3-8B-Instruct-v0.9-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [Llama-3-8B-Instruct-v0.9-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-v0.9-GGUF/tree/main/Llama-3-8B-Instruct-v0.9-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-v0.9-GGUF --include "Llama-3-8B-Instruct-v0.9-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-v0.9-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```