README.md

metadata

language:
  - en
  - vi
license: mit
library_name: transformers
tags:
  - ghost
  - TensorBlock
  - GGUF
pipeline_tag: text-generation
widget:
  - text: How many helicopters can a human eat in one sitting
    output:
      text: >-
        Ahoy, me matey! A human can eat approximately one helicopter in one
        sitting, but only if they're a giant sea monster with a stomach the size
        of a small country. 🤢🤢 So, it's not advisable to try this, pirate!
        🏰🛢️
base_model: ghost-x/ghost-7b-v0.9.1
model-index:
  - name: ghost-7b-v0.9.1
    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: 55.38
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.1
          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: 77.03
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.1
          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: 54.78
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.1
          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: 43.96
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.1
          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: 72.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.1
          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: 26.91
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.1
          name: Open LLM Leaderboard

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

ghost-x/ghost-7b-v0.9.1 - GGUF

This repo contains GGUF format model files for ghost-x/ghost-7b-v0.9.1.

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

<|system|>
{system_prompt}</s>
<|user|>
{prompt}</s>
<|assistant|>

Model file specification

Filename	Quant type	File Size	Description
ghost-7b-v0.9.1-Q2_K.gguf	Q2_K	2.532 GB	smallest, significant quality loss - not recommended for most purposes
ghost-7b-v0.9.1-Q3_K_S.gguf	Q3_K_S	2.947 GB	very small, high quality loss
ghost-7b-v0.9.1-Q3_K_M.gguf	Q3_K_M	3.277 GB	very small, high quality loss
ghost-7b-v0.9.1-Q3_K_L.gguf	Q3_K_L	3.560 GB	small, substantial quality loss
ghost-7b-v0.9.1-Q4_0.gguf	Q4_0	3.827 GB	legacy; small, very high quality loss - prefer using Q3_K_M
ghost-7b-v0.9.1-Q4_K_S.gguf	Q4_K_S	3.856 GB	small, greater quality loss
ghost-7b-v0.9.1-Q4_K_M.gguf	Q4_K_M	4.068 GB	medium, balanced quality - recommended
ghost-7b-v0.9.1-Q5_0.gguf	Q5_0	4.654 GB	legacy; medium, balanced quality - prefer using Q4_K_M
ghost-7b-v0.9.1-Q5_K_S.gguf	Q5_K_S	4.654 GB	large, low quality loss - recommended
ghost-7b-v0.9.1-Q5_K_M.gguf	Q5_K_M	4.779 GB	large, very low quality loss - recommended
ghost-7b-v0.9.1-Q6_K.gguf	Q6_K	5.534 GB	very large, extremely low quality loss
ghost-7b-v0.9.1-Q8_0.gguf	Q8_0	7.167 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/ghost-7b-v0.9.1-GGUF --include "ghost-7b-v0.9.1-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/ghost-7b-v0.9.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'