README.md

---
language:
- en
license: other
library_name: transformers
tags:
- not-for-all-audiences
- axolotl
- qlora
- llama-cpp
- gguf-my-repo
base_model: invisietch/MiS-Firefly-v0.2-22B
model-index:
- name: MiS-Firefly-v0.2-22B
  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: 53.71
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=invisietch/MiS-Firefly-v0.2-22B
      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: 36.08
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=invisietch/MiS-Firefly-v0.2-22B
      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: 15.94
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=invisietch/MiS-Firefly-v0.2-22B
      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: 7.27
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=invisietch/MiS-Firefly-v0.2-22B
      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: 17.81
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=invisietch/MiS-Firefly-v0.2-22B
      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: 29.11
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=invisietch/MiS-Firefly-v0.2-22B
      name: Open LLM Leaderboard
---

# Triangle104/MiS-Firefly-v0.2-22B-Q4_K_M-GGUF
This model was converted to GGUF format from [`invisietch/MiS-Firefly-v0.2-22B`](https://huggingface.co/invisietch/MiS-Firefly-v0.2-22B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/invisietch/MiS-Firefly-v0.2-22B) for more details on the model.

---
Model details:
-
This is a fix for the quantization issue in Firefly v0.1.

Firefly is a Mistral Small 22B finetune designed for creative writing and roleplay. The model is largely uncensored and should support context up to 32,768 tokens.

The model has been tested in various roleplay scenarios up to 16k context, as well as in a role as an assistant. It shows a broad competency & coherence across various scenarios.

Special thanks to SicariusSicariiStuff for bouncing ideas back & forth on training, and SytanSD for quants.

Feedback
-
I appreciate all feedback on any of my models, you can use:

    My Discord server - requires Discord.
    The Community tab - requires HF login.
    Discord DMs to invisietch.

Your feedback is how I improve these models for future versions.

Disclaimer
-
This model is extensively uncensored. It can generate explicit, disturbing or offensive responses. Use responsibly. I am not responsible for your use of this model.

This model is a finetune of Mistral Small 22B (2409) and usage must follow the terms of Mistral's license. By downloading this model, you agree not to use it for commercial purposes unless you have a valid Mistral commercial license. See the base model card for more details.

Prompting Format
-
I'd recommend Mistral v2 & v3 prompting format:

<s>[INST] User message here.[/INST] Bot response here</s>[INST] User message 2 here.[/INST]

If you're using SillyTavern, make sure the story string is set correctly to Mistral v2 & v3 (not v3 Tekken):

[INST] {{#if system}}{{system}}
{{/if}}{{#if wiBefore}}{{wiBefore}}
{{/if}}{{#if description}}{{description}}
{{/if}}{{#if personality}}{{personality}}
{{/if}}{{#if scenario}}{{scenario}}
{{/if}}{{#if wiAfter}}{{wiAfter}}
{{/if}}{{#if persona}}{{persona}}
{{/if}}{{trim}}[/INST] Understood.</s>

The model seems very sensitive to wrong prompting formats.

Sampler Settings
-
I'm running the following sampler settings but this is an RC and they may not be optimal.

    Temperature: 1
    Min-P: 0.1
    Rep Pen: 1.08
    Rep Pen Range: 1536
    XTC: 0.1/0.15

If you get completely incoherent responses, feel free to use these as a starting point.

High temperature settings (above 1) tend to create less coherent responses.

Training Strategy
-
I started with a finetune of Mistral Small 22B which had been trained on the Gutenberg dataset: nbeerbower/Mistral-Small-Gutenberg-Doppel-22B.

The first stage of my training was a single epoch at low LR over a 474 million token text completion dataset.

I followed this up with a coherence, decensorship & roleplay finetune over a 172 million token instruct dataset over two epochs.

I did a slerp merge of epoch 1 into epoch 2 at a light weight which resolved the name-spelling issues on quantized versions of Firefly v0.1.

Total training time was about 32hrs on 4x Nvidia A100 80GB.

Built with Axolotl 

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_invisietch__MiS-Firefly-v0.2-22B) 

---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo Triangle104/MiS-Firefly-v0.2-22B-Q4_K_M-GGUF --hf-file mis-firefly-v0.2-22b-q4_k_m.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/MiS-Firefly-v0.2-22B-Q4_K_M-GGUF --hf-file mis-firefly-v0.2-22b-q4_k_m.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) 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/MiS-Firefly-v0.2-22B-Q4_K_M-GGUF --hf-file mis-firefly-v0.2-22b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/MiS-Firefly-v0.2-22B-Q4_K_M-GGUF --hf-file mis-firefly-v0.2-22b-q4_k_m.gguf -c 2048
```