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-3.2-SUN-2.5B-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-SUN-2.5B-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.2-SUN-2.5B-chat-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9979551e42ec9ea02bb9d3417403f2844834024a7f83437d6970b455ed5181
+size 1024635744

Llama-3.2-SUN-2.5B-chat-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1180491a6bb7a9055423c3803268b1934db773a44a8f1dc5ca55032be6264a
+size 1354613600

Llama-3.2-SUN-2.5B-chat-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084f29e465fb14d9f14a7f77b89aac0c80b18fad7a14a0023a629e7cede803d0
+size 1270989664

Llama-3.2-SUN-2.5B-chat-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ea4e496955d074d20fba63549877b61c29ea11cd09423cfbdb144bae1fd18f
+size 1172947808

Llama-3.2-SUN-2.5B-chat-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16d69bc7288d6cef4596e5959358c050042d9771124ecc1e9a2d325c18f71d8
+size 1466307424

Llama-3.2-SUN-2.5B-chat-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2764b3366fc84f2f9fb11e712946a7ff0554f6dcd4b47abf449f4981be22161a
+size 1539838816

Llama-3.2-SUN-2.5B-chat-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ff89c8986f0f5c1bc414d4ad5cb8117ba6bbfed197ecae2346bb1f1f30659d
+size 1475220320

Llama-3.2-SUN-2.5B-chat-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74d5bb09f9e997a7ea2ff5a33971de4cbaf0e89b483cc6bcbe0d5b223bb444f
+size 1742410592

Llama-3.2-SUN-2.5B-chat-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb6ef9fc4533c2ff2ba7750006aac5dcf0e37b2263a05779243a6b934032638
+size 1780290400

Llama-3.2-SUN-2.5B-chat-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5e63208af9c94affdc5b13ac725cf35fee96ecdbf01e70b76562208328bdbe
+size 1742410592

Llama-3.2-SUN-2.5B-chat-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c87ba6570cd8e096afc9acccabd8d140d93c82f6e4de7608350a3d4fc25fa1
+size 2035770208

Llama-3.2-SUN-2.5B-chat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e254e41bcc12641b61b6d4e7d5ac28573d5111cf2e2d3e77df77fbdf847167
+size 2634335072

README.md

@@ -0,0 +1,190 @@
+---
+language:
+- en
+license: llama3.2
+library_name: transformers
+base_model: meditsolutions/Llama-3.2-SUN-2.5B-chat
+datasets:
+- argilla/OpenHermesPreferences
+- argilla/magpie-ultra-v0.1
+- argilla/Capybara-Preferences-Filtered
+- mlabonne/open-perfectblend
+- HuggingFaceTB/everyday-conversations-llama3.1-2k
+- WizardLMTeam/WizardLM_evol_instruct_V2_196k
+- ProlificAI/social-reasoning-rlhf
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: Llama-3.2-SUN-2.5B-chat
+  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: 56.04
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
+      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: 9.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
+      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: 5.06
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
+      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: 1.23
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
+      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: 1.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
+      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: 9.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
+      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>
+
+## meditsolutions/Llama-3.2-SUN-2.5B-chat - GGUF
+
+This repo contains GGUF format model files for [meditsolutions/Llama-3.2-SUN-2.5B-chat](https://huggingface.co/meditsolutions/Llama-3.2-SUN-2.5B-chat).
+
+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).
+
+<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
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+Cutting Knowledge Date: December 2023
+Today Date: 25 Nov 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-3.2-SUN-2.5B-chat-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q2_K.gguf) | Q2_K | 1.025 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.2-SUN-2.5B-chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q3_K_S.gguf) | Q3_K_S | 1.173 GB | very small, high quality loss |
+| [Llama-3.2-SUN-2.5B-chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q3_K_M.gguf) | Q3_K_M | 1.271 GB | very small, high quality loss |
+| [Llama-3.2-SUN-2.5B-chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q3_K_L.gguf) | Q3_K_L | 1.355 GB | small, substantial quality loss |
+| [Llama-3.2-SUN-2.5B-chat-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q4_0.gguf) | Q4_0 | 1.466 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.2-SUN-2.5B-chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q4_K_S.gguf) | Q4_K_S | 1.475 GB | small, greater quality loss |
+| [Llama-3.2-SUN-2.5B-chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q4_K_M.gguf) | Q4_K_M | 1.540 GB | medium, balanced quality - recommended |
+| [Llama-3.2-SUN-2.5B-chat-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q5_0.gguf) | Q5_0 | 1.742 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.2-SUN-2.5B-chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q5_K_S.gguf) | Q5_K_S | 1.742 GB | large, low quality loss - recommended |
+| [Llama-3.2-SUN-2.5B-chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q5_K_M.gguf) | Q5_K_M | 1.780 GB | large, very low quality loss - recommended |
+| [Llama-3.2-SUN-2.5B-chat-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q6_K.gguf) | Q6_K | 2.036 GB | very large, extremely low quality loss |
+| [Llama-3.2-SUN-2.5B-chat-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q8_0.gguf) | Q8_0 | 2.634 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-3.2-SUN-2.5B-chat-GGUF --include "Llama-3.2-SUN-2.5B-chat-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-3.2-SUN-2.5B-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```