README.md

metadata

license: other
library_name: transformers
tags:
  - chatml
  - finetune
  - gpt4
  - synthetic data
  - custom_code
  - qwen2
  - TensorBlock
  - GGUF
datasets:
  - Locutusque/Hercules-v3.0
license_name: tongyi-qianwen-research
license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat/raw/main/LICENSE
base_model: aloobun/Reyna-Mini-1.8B-v0.2
model-index:
  - name: Reyna-Mini-1.8B-v0.2
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 36.6
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 60.19
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 44.75
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 41.24
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 61.56
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 31.31
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aloobun/Reyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard

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

aloobun/Reyna-Mini-1.8B-v0.2 - GGUF

This repo contains GGUF format model files for aloobun/Reyna-Mini-1.8B-v0.2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Run them on the TensorBlock client using your local machine ↗

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
Reyna-Mini-1.8B-v0.2-Q2_K.gguf	Q2_K	0.847 GB	smallest, significant quality loss - not recommended for most purposes
Reyna-Mini-1.8B-v0.2-Q3_K_S.gguf	Q3_K_S	0.954 GB	very small, high quality loss
Reyna-Mini-1.8B-v0.2-Q3_K_M.gguf	Q3_K_M	1.016 GB	very small, high quality loss
Reyna-Mini-1.8B-v0.2-Q3_K_L.gguf	Q3_K_L	1.056 GB	small, substantial quality loss
Reyna-Mini-1.8B-v0.2-Q4_0.gguf	Q4_0	1.120 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Reyna-Mini-1.8B-v0.2-Q4_K_S.gguf	Q4_K_S	1.158 GB	small, greater quality loss
Reyna-Mini-1.8B-v0.2-Q4_K_M.gguf	Q4_K_M	1.218 GB	medium, balanced quality - recommended
Reyna-Mini-1.8B-v0.2-Q5_0.gguf	Q5_0	1.311 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Reyna-Mini-1.8B-v0.2-Q5_K_S.gguf	Q5_K_S	1.328 GB	large, low quality loss - recommended
Reyna-Mini-1.8B-v0.2-Q5_K_M.gguf	Q5_K_M	1.377 GB	large, very low quality loss - recommended
Reyna-Mini-1.8B-v0.2-Q6_K.gguf	Q6_K	1.579 GB	very large, extremely low quality loss
Reyna-Mini-1.8B-v0.2-Q8_0.gguf	Q8_0	1.958 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/Reyna-Mini-1.8B-v0.2-GGUF --include "Reyna-Mini-1.8B-v0.2-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/Reyna-Mini-1.8B-v0.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'