README.md

metadata

language:
  - en
license: llama3
library_name: transformers
tags:
  - axolotl
  - finetune
  - dpo
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3
  - chatml
  - TensorBlock
  - GGUF
base_model: MaziyarPanahi/calme-2.3-llama3-70b
datasets:
  - MaziyarPanahi/truthy-dpo-v0.1-axolotl
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
  - name: calme-2.3-llama3-70b
    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: 72.35
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
          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: 86
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
          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: 80.47
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
          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: 63.45
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
          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: 82.95
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
          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: 87.19
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/calme-2.3-llama3-70b
          name: Open LLM Leaderboard

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

MaziyarPanahi/calme-2.3-llama3-70b - GGUF

This repo contains GGUF format model files for MaziyarPanahi/calme-2.3-llama3-70b.

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
calme-2.3-llama3-70b-Q2_K.gguf	Q2_K	26.375 GB	smallest, significant quality loss - not recommended for most purposes
calme-2.3-llama3-70b-Q3_K_S.gguf	Q3_K_S	30.912 GB	very small, high quality loss
calme-2.3-llama3-70b-Q3_K_M.gguf	Q3_K_M	34.268 GB	very small, high quality loss
calme-2.3-llama3-70b-Q3_K_L.gguf	Q3_K_L	37.141 GB	small, substantial quality loss
calme-2.3-llama3-70b-Q4_0.gguf	Q4_0	39.970 GB	legacy; small, very high quality loss - prefer using Q3_K_M
calme-2.3-llama3-70b-Q4_K_S.gguf	Q4_K_S	40.347 GB	small, greater quality loss
calme-2.3-llama3-70b-Q4_K_M.gguf	Q4_K_M	42.520 GB	medium, balanced quality - recommended
calme-2.3-llama3-70b-Q5_0.gguf	Q5_0	48.657 GB	legacy; medium, balanced quality - prefer using Q4_K_M
calme-2.3-llama3-70b-Q5_K_S.gguf	Q5_K_S	48.657 GB	large, low quality loss - recommended
calme-2.3-llama3-70b-Q5_K_M.gguf	Q5_K_M	49.950 GB	large, very low quality loss - recommended
calme-2.3-llama3-70b-Q8_0	Q6_K	74.975 GB	very large, extremely low quality loss
calme-2.3-llama3-70b-Q6_K	Q8_0	57.888 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/calme-2.3-llama3-70b-GGUF --include "calme-2.3-llama3-70b-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/calme-2.3-llama3-70b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'