Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ 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
+Llama3.3-70B-CogniLink-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q6_K/Llama3.3-70B-CogniLink-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q6_K/Llama3.3-70B-CogniLink-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q8_0/Llama3.3-70B-CogniLink-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q8_0/Llama3.3-70B-CogniLink-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.3-70B-CogniLink-Q8_0/Llama3.3-70B-CogniLink-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

Llama3.3-70B-CogniLink-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4cf99700a712fe0eaaf66487018af098652ccc9eb9fe054d3ee3045bdea501
+size 26375110528

Llama3.3-70B-CogniLink-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8ea0c350475fdd85bf2e4073e06cd05e708f48ea218d3a92d66fffcdbb1edc
+size 37140594560

Llama3.3-70B-CogniLink-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c3dd6dd8d5e3f2ec83dd83ba9bdd86328bf41e97bee5176bf03ff4dd7ee97c
+size 34267496320

Llama3.3-70B-CogniLink-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2a4e9fd1540da208d9b6989ef986ce1e3cd628028ec1828054b522439a16cc
+size 30912053120

Llama3.3-70B-CogniLink-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d329dcdb8cb5fbc7d8f6c93dbc1106a63a6dbdc81e5f559fa6e34ab57cfa58f6
+size 39969734528

Llama3.3-70B-CogniLink-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c694fcc864a05af65e0417688e9ba5fc186b3747de8a4cfef0b05bcd6a10ff8e
+size 42520395648

Llama3.3-70B-CogniLink-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878a80b11d7ecd7e73fa78046bf24cbeaadd1a2c03f6a8e7613fca42ab60ac7b
+size 40347221888

Llama3.3-70B-CogniLink-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29969e857706550d670ca65e2165f07717d009b6a772e134ff4c91789bfb31c
+size 48657448832

Llama3.3-70B-CogniLink-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef4b18fbd2a8ea79a4130a071d4b2f7fc86081e160e45c9d5e11006158d8586
+size 49949818752

Llama3.3-70B-CogniLink-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a9d2410f94e4a720021b78d040cf5d6961c25921c565e30e97c2c91d65bc35
+size 48657448832

Llama3.3-70B-CogniLink-Q6_K/Llama3.3-70B-CogniLink-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c4cd8fa3a57f39a25a42adb519d18ebf0240515855e099261dcb5d16cd6129
+size 34847472544

Llama3.3-70B-CogniLink-Q6_K/Llama3.3-70B-CogniLink-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854d012a1763ad2e73febf58d74f02f4a53d26604e72c4a0571e834ff715c74e
+size 23040672928

Llama3.3-70B-CogniLink-Q8_0/Llama3.3-70B-CogniLink-Q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66a8369d2da0a80e4a23612be9766c4914a84d71e3feace5ea765f7f052a7cb
+size 34980012992

Llama3.3-70B-CogniLink-Q8_0/Llama3.3-70B-CogniLink-Q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f27033c46022c83a40108543bfd8597f8b3b542ccb118545548b70a64dbab94
+size 34949976384

Llama3.3-70B-CogniLink-Q8_0/Llama3.3-70B-CogniLink-Q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa14cbd5e6403b3753615babedefc3ac65b849d6d07f1a1184bb10027f3c313f
+size 5045062560

README.md

@@ -0,0 +1,193 @@
+---
+base_model: Daemontatox/Llama3.3-70B-CogniLink
+tags:
+- state-of-the-art
+- reasoning
+- chain-of-thought
+- text-generation
+- transformers
+- llama
+- instruction-tuning
+- TensorBlock
+- GGUF
+license: apache-2.0
+language:
+- en
+datasets:
+- Daemontatox/Deepthinking-COT
+- gghfez/QwQ-LongCoT-130K-cleaned
+pipeline_tag: text-generation
+library_name: transformers
+model-index:
+- name: Llama3.3-70B-CogniLink
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 69.31
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 52.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 39.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 26.06
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
+      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: 21.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
+      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: 46.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Daemontatox%2FLlama3.3-70B-CogniLink
+      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>
+
+## Daemontatox/Llama3.3-70B-CogniLink - GGUF
+
+This repo contains GGUF format model files for [Daemontatox/Llama3.3-70B-CogniLink](https://huggingface.co/Daemontatox/Llama3.3-70B-CogniLink).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
+
+<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 |
+| -------- | ---------- | --------- | ----------- |
+| [Llama3.3-70B-CogniLink-Q2_K.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama3.3-70B-CogniLink-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
+| [Llama3.3-70B-CogniLink-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
+| [Llama3.3-70B-CogniLink-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
+| [Llama3.3-70B-CogniLink-Q4_0.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama3.3-70B-CogniLink-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
+| [Llama3.3-70B-CogniLink-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
+| [Llama3.3-70B-CogniLink-Q5_0.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama3.3-70B-CogniLink-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
+| [Llama3.3-70B-CogniLink-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
+| [Llama3.3-70B-CogniLink-Q6_K](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
+| [Llama3.3-70B-CogniLink-Q8_0](https://huggingface.co/tensorblock/Llama3.3-70B-CogniLink-GGUF/blob/main/Llama3.3-70B-CogniLink-Q8_0) | Q8_0 | 74.975 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/Llama3.3-70B-CogniLink-GGUF --include "Llama3.3-70B-CogniLink-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/Llama3.3-70B-CogniLink-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```