base_model: Sao10K/Llama-3.1-8B-Stheno-v3.4
datasets:
- Setiaku/Stheno-v3.4-Instruct
- Setiaku/Stheno-3.4-Creative-2
language:
- en
license: cc-by-nc-4.0
tags:
- llama-cpp
- gguf-my-repo
Llama-3.1-8B-Stheno-v3.4
This model has went through a multi-stage finetuning process.
- 1st, over a multi-turn Conversational-Instruct
- 2nd, over a Creative Writing / Roleplay along with some Creative-based Instruct Datasets.
- - Dataset consists of a mixture of Human and Claude Data.
Prompting Format:
- Use the L3 Instruct Formatting - Euryale 2.1 Preset Works Well
- Temperature + min_p as per usual, I recommend 1.4 Temp + 0.2 min_p.
- Has a different vibe to previous versions. Tinker around.
Changes since previous Stheno Datasets:
- Included Multi-turn Conversation-based Instruct Datasets to boost multi-turn coherency. # This is a seperate set, not the ones made by Kalomaze and Nopm, that are used in Magnum. They're completely different data.
- Replaced Single-Turn Instruct with Better Prompts and Answers by Claude 3.5 Sonnet and Claude 3 Opus.
- Removed c2 Samples -> Underway of re-filtering and masking to use with custom prefills. TBD
- Included 55% more Roleplaying Examples based of [Gryphe's](https://huggingface.co/datasets/Gryphe/Sonnet3.5-Charcard-Roleplay) Charcard RP Sets. Further filtered and cleaned on.
- Included 40% More Creative Writing Examples.
- Included Datasets Targeting System Prompt Adherence.
- Included Datasets targeting Reasoning / Spatial Awareness.
- Filtered for the usual errors, slop and stuff at the end. Some may have slipped through, but I removed nearly all of it.
Personal Opinions:
- Llama3.1 was more disappointing, in the Instruct Tune? It felt overbaked, atleast. Likely due to the DPO being done after their SFT Stage.
- Tuning on L3.1 base did not give good results, unlike when I tested with Nemo base. unfortunate.
- Still though, I think I did an okay job. It does feel a bit more distinctive.
- It took a lot of tinkering, like a LOT to wrangle this.
Below are some graphs and all for you to observe.
Turn Distribution # 1 Turn is considered as 1 combined Human/GPT pair in a ShareGPT format. 4 Turns means 1 System Row + 8 Human/GPT rows in total.
Token Count Histogram # Based on the Llama 3 Tokenizer
Source Image: https://www.pixiv.net/en/artworks/91689070
DarqueDante/Llama-3.1-8B-Stheno-v3.4-IQ4_XS-GGUF
This model was converted to GGUF format from Sao10K/Llama-3.1-8B-Stheno-v3.4 using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
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 DarqueDante/Llama-3.1-8B-Stheno-v3.4-IQ4_XS-GGUF --hf-file llama-3.1-8b-stheno-v3.4-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo DarqueDante/Llama-3.1-8B-Stheno-v3.4-IQ4_XS-GGUF --hf-file llama-3.1-8b-stheno-v3.4-iq4_xs-imat.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 DarqueDante/Llama-3.1-8B-Stheno-v3.4-IQ4_XS-GGUF --hf-file llama-3.1-8b-stheno-v3.4-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo DarqueDante/Llama-3.1-8B-Stheno-v3.4-IQ4_XS-GGUF --hf-file llama-3.1-8b-stheno-v3.4-iq4_xs-imat.gguf -c 2048