README.md

metadata

base_model: flammenai/Flammades-Mistral-Nemo-12B
datasets:
  - flammenai/Date-DPO-NoAsterisks
  - jondurbin/truthy-dpo-v0.1
library_name: transformers
license: apache-2.0
tags:
  - llama-cpp
  - gguf-my-repo
model-index:
  - name: Flammades-Mistral-Nemo-12B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 38.42
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 32.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 6.19
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 7.16
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
          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: 20.31
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
          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: 29.57
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Flammades-Mistral-Nemo-12B
          name: Open LLM Leaderboard

Triangle104/Flammades-Mistral-Nemo-12B-Q4_K_M-GGUF

This model was converted to GGUF format from flammenai/Flammades-Mistral-Nemo-12B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Model details:

nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2 finetuned on flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1. Method

ORPO tuned with 2x RTX 3090 for 3 epochs. Open LLM Leaderboard Evaluation Results

Detailed results can be found here Metric Value Avg. 22.34 IFEval (0-Shot) 38.42 BBH (3-Shot) 32.39 MATH Lvl 5 (4-Shot) 6.19 GPQA (0-shot) 7.16 MuSR (0-shot) 20.31 MMLU-PRO (5-shot) 29.57

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q4_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q4_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q4_k_m.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q4_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Flammades-Mistral-Nemo-12B-Q4_K_M-GGUF --hf-file flammades-mistral-nemo-12b-q4_k_m.gguf -c 2048