README.md

metadata

license: llama3
language:
  - tr
  - en
base_model: curiositytech/MARS
pipeline_tag: text-generation
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: MARS
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge TR v0.2
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc
            value: 46.08
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU TR v0.2
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 47.02
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA TR v0.2
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: acc
            value: 49.38
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande TR v0.2
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 53.71
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k TR v0.2
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 53.08
            name: accuracy

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

curiositytech/MARS - GGUF

This repo contains GGUF format model files for curiositytech/MARS.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

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
MARS-Q2_K.gguf	Q2_K	2.961 GB	smallest, significant quality loss - not recommended for most purposes
MARS-Q3_K_S.gguf	Q3_K_S	3.413 GB	very small, high quality loss
MARS-Q3_K_M.gguf	Q3_K_M	3.743 GB	very small, high quality loss
MARS-Q3_K_L.gguf	Q3_K_L	4.025 GB	small, substantial quality loss
MARS-Q4_0.gguf	Q4_0	4.341 GB	legacy; small, very high quality loss - prefer using Q3_K_M
MARS-Q4_K_S.gguf	Q4_K_S	4.370 GB	small, greater quality loss
MARS-Q4_K_M.gguf	Q4_K_M	4.583 GB	medium, balanced quality - recommended
MARS-Q5_0.gguf	Q5_0	5.215 GB	legacy; medium, balanced quality - prefer using Q4_K_M
MARS-Q5_K_S.gguf	Q5_K_S	5.215 GB	large, low quality loss - recommended
MARS-Q5_K_M.gguf	Q5_K_M	5.339 GB	large, very low quality loss - recommended
MARS-Q6_K.gguf	Q6_K	6.143 GB	very large, extremely low quality loss
MARS-Q8_0.gguf	Q8_0	7.954 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/MARS-GGUF --include "MARS-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/MARS-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'