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-3.2-3B-Overthinker-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-3B-Overthinker-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.2-3B-Overthinker-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf4fdc8a8bef2a9f5ca43df2841cb2df137aeaaaefc5070057b617aea37b204
+size 1363932704

Llama-3.2-3B-Overthinker-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22420e5548a1d2ea3d95e16231db969362eff030117434cc6c2c6999397d3d7
+size 1815344672

Llama-3.2-3B-Overthinker-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c17c0a1c4b974f3381d783446e5346476d6e23697dac47f05e4076f06d16e1
+size 1687156256

Llama-3.2-3B-Overthinker-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ad0fa431da411ed88424fac573ba746a31c88013c7742f4eae32fadceca65a
+size 1542845984

Llama-3.2-3B-Overthinker-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be82573a714d3fcd58471916af2eb4913829dae2f949a5c9689d3c109df8b761
+size 1917187616

Llama-3.2-3B-Overthinker-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78fed2dc7e2e472cc13cf209ec81753195885160a4a401943bb64a5461bf35c
+size 2019374624

Llama-3.2-3B-Overthinker-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef9c848ef43fd4ac4866d8106a46b2c737eb05349b843f9f73d0a18e4e0b774
+size 1928197664

Llama-3.2-3B-Overthinker-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed465b0c580f47cd6ab6fc8e1a6e8dfe4afa7d68d220774af2be2e89da1c9ed
+size 2269509152

Llama-3.2-3B-Overthinker-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac83ac1ab9ed7efa1a6cd332db282c47199c06c004ae1c56e1b8e8fc548f9d1
+size 2322150944

Llama-3.2-3B-Overthinker-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2d873b59355c60de7131732f21884583462b1852ef865fb52e6131a238888c
+size 2269509152

Llama-3.2-3B-Overthinker-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db81b44e5cd9494e30aabee11524fd31bf6aafc54b9adc30407e98ff899ae06
+size 2643850784

Llama-3.2-3B-Overthinker-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f090e5091a988954b61bd3e6a14218d3056b54eba429add2e44839e0ea51f29
+size 3421896224

README.md

@@ -0,0 +1,186 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- sft
+- TensorBlock
+- GGUF
+base_model: Lyte/Llama-3.2-3B-Overthinker
+datasets:
+- Lyte/Reasoning-Paused
+pipeline_tag: text-generation
+model-index:
+- name: Llama-3.2-3B-Overthinker
+  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: 64.08
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.2-3B-Overthinker
+      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: 20.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.2-3B-Overthinker
+      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: 2.64
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.2-3B-Overthinker
+      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=Lyte/Llama-3.2-3B-Overthinker
+      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: 3.9
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.2-3B-Overthinker
+      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: 22.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lyte/Llama-3.2-3B-Overthinker
+      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>
+
+## Lyte/Llama-3.2-3B-Overthinker - GGUF
+
+This repo contains GGUF format model files for [Lyte/Llama-3.2-3B-Overthinker](https://huggingface.co/Lyte/Llama-3.2-3B-Overthinker).
+
+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|>
+{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-3.2-3B-Overthinker-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q2_K.gguf) | Q2_K | 1.364 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3.2-3B-Overthinker-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q3_K_S.gguf) | Q3_K_S | 1.543 GB | very small, high quality loss |
+| [Llama-3.2-3B-Overthinker-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q3_K_M.gguf) | Q3_K_M | 1.687 GB | very small, high quality loss |
+| [Llama-3.2-3B-Overthinker-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q3_K_L.gguf) | Q3_K_L | 1.815 GB | small, substantial quality loss |
+| [Llama-3.2-3B-Overthinker-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q4_0.gguf) | Q4_0 | 1.917 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3.2-3B-Overthinker-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q4_K_S.gguf) | Q4_K_S | 1.928 GB | small, greater quality loss |
+| [Llama-3.2-3B-Overthinker-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q4_K_M.gguf) | Q4_K_M | 2.019 GB | medium, balanced quality - recommended |
+| [Llama-3.2-3B-Overthinker-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q5_0.gguf) | Q5_0 | 2.270 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3.2-3B-Overthinker-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q5_K_S.gguf) | Q5_K_S | 2.270 GB | large, low quality loss - recommended |
+| [Llama-3.2-3B-Overthinker-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q5_K_M.gguf) | Q5_K_M | 2.322 GB | large, very low quality loss - recommended |
+| [Llama-3.2-3B-Overthinker-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q6_K.gguf) | Q6_K | 2.644 GB | very large, extremely low quality loss |
+| [Llama-3.2-3B-Overthinker-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Overthinker-GGUF/blob/main/Llama-3.2-3B-Overthinker-Q8_0.gguf) | Q8_0 | 3.422 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-3.2-3B-Overthinker-GGUF --include "Llama-3.2-3B-Overthinker-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-3.2-3B-Overthinker-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```