README.md

metadata

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

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

Daemontatox/Llama3.3-70B-CogniLink - GGUF

This repo contains GGUF format model files for Daemontatox/Llama3.3-70B-CogniLink.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Run them on the TensorBlock client using your local machine ↗

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	Q2_K	26.375 GB	smallest, significant quality loss - not recommended for most purposes
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	Q3_K_M	34.267 GB	very small, high quality loss
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	Q4_0	39.970 GB	legacy; small, very high quality loss - prefer using Q3_K_M
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	Q4_K_M	42.520 GB	medium, balanced quality - recommended
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	Q5_K_S	48.657 GB	large, low quality loss - recommended
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	Q6_K	57.888 GB	very large, extremely low quality loss
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

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

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:

huggingface-cli download tensorblock/Llama3.3-70B-CogniLink-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'