Triangle104/Rombos-Qwen2.5-Writer-32b-Q3_K_M-GGUF

This model was converted to GGUF format from SubtleOne/Rombos-Qwen2.5-Writer-32b 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:

This model is a merge using Rombos's top-ranked 32b model, based on Qwen 2.5, and merging three creative writing finetunes. The creative content is a serious upgrade over the base it started with, and I enjoyed it in my DnD RPG campaign.

    Merge

This is a merge of pre-trained language models created using mergekit.

    Merge Method

This model was merged using the DELLA merge method using Rombos-LLM-V2.5-Qwen-32b as a base.

    Models Merged

The following models were included in the merge:

EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 allura-org/Qwen2.5-32b-RP-Ink nbeerbower/Qwen2.5-Gutenberg-Doppel-32B

    Configuration

The following YAML configuration was used to produce this model:

base_model: rombodawg/Rombos-LLM-V2.5-Qwen-32b parameters: int8_mask: true rescale: false normalize: true dtype: bfloat16 tokenizer_source: union merge_method: dare_ties models:

• model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 parameters: weight: [0.4] density: [0.55]
• model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B parameters: weight: [0.3] density: [0.55]
• model: allura-org/Qwen2.5-32b-RP-Ink parameters: weight: [0.4] density: [0.55]

---

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/Rombos-Qwen2.5-Writer-32b-Q3_K_M-GGUF --hf-file rombos-qwen2.5-writer-32b-q3_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Rombos-Qwen2.5-Writer-32b-Q3_K_M-GGUF --hf-file rombos-qwen2.5-writer-32b-q3_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/Rombos-Qwen2.5-Writer-32b-Q3_K_M-GGUF --hf-file rombos-qwen2.5-writer-32b-q3_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Rombos-Qwen2.5-Writer-32b-Q3_K_M-GGUF --hf-file rombos-qwen2.5-writer-32b-q3_k_m.gguf -c 2048