RichardErkhov/Epiculous_-_Azure_Dusk-v0.2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Azure_Dusk-v0.2 - GGUF

• —Model creator: https://huggingface.co/Epiculous/
• —Original model: https://huggingface.co/Epiculous/Azure_Dusk-v0.2/

Original model description: --- language:

• —en
• —fr
• —de
• —es
• —it
• —pt
• —ru
• —zh
• —ja license: apache-2.0 datasets:
• —Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
• —anthracite-org/stheno-filtered-v1.1
• —PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
• —Gryphe/Sonnet3.5-Charcard-Roleplay
• —Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
• —anthracite-org/kalo-opus-instruct-22k-no-refusal
• —anthracite-org/nopmclaudewriting_fixed
• —anthracite-org/kaloopusmisc240827 pipelinetag: text-generation model-index:
• —name: Azure_Dusk-v0.2 results:
• —task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: numfewshot: 0 metrics:
• —type: instlevelstrictacc and promptlevelstrictacc value: 34.67 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/openllmleaderboard?query=Epiculous/Azure_Dusk-v0.2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: numfewshot: 3 metrics:
• —type: accnorm value: 17.4 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/openllmleaderboard?query=Epiculous/AzureDusk-v0.2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competitionmath args: numfew_shot: 4 metrics:
• —type: exactmatch value: 1.66 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/openllmleaderboard?query=Epiculous/AzureDusk-v0.2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: numfewshot: 0 metrics:
• —type: accnorm value: 1.45 name: accnorm source: url: https://huggingface.co/spaces/open-llm-leaderboard/openllmleaderboard?query=Epiculous/Azure_Dusk-v0.2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: numfewshot: 0 metrics:
• —type: accnorm value: 6.37 name: accnorm source: url: https://huggingface.co/spaces/open-llm-leaderboard/openllmleaderboard?query=Epiculous/Azure_Dusk-v0.2 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: numfewshot: 5 metrics:
• —type: acc value: 22.6 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/openllmleaderboard?query=Epiculous/Azure_Dusk-v0.2 name: Open LLM Leaderboard ---

Following up on CrimsonDawn-v0.2 we have AzureDusk-v0.2! Training on Mistral-Nemo-Base-2407 this time I've added significantly more data, as well as trained using RSLoRA as opposed to regular LoRA. Another key change is training on ChatML as opposed to Mistral Formatting.

Quants!

<strong>full</strong> / exl2 / gguf

Prompting

The v0.2 models are trained on ChatML, the prompting structure goes a little something like this:

<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant

Context and Instruct

The v0.2 models are trained on ChatML, please use that Context and Instruct template.

Current Top Sampler Settings

Spicy_Temp <br/> Violet_Twilight-Nitral-Special <br/>

Training

Training was done twice over 2 epochs each on two 2x NVIDIA A6000 GPUs using LoRA. A two-phased approach was used in which the base model was trained 2 epochs on RP data, the LoRA was then applied to base. Finally, the new modified base was trained 2 epochs on instruct, and the new instruct LoRA was applied to the modified base, resulting in what you see here.

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Open LLM Leaderboard Evaluation Results

Detailed results can be found here