Triangle104/EVA-Qwen2.5-32B-v0.2-Q5_K_M-GGUF

This model was converted to GGUF format from EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 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:

A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data.

It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model.

Dedicated to Nev.

Version notes for 0.2: Basically, reprocessed the whole dataset again, due to a severe mistake in previously used pipeline, which left the data poisoned with a lot of non-unicode characters. Now, no more weird generation artifacts, and more stability. Major kudos to Cahvay for his work on fixing this critical issue.

Prompt format is ChatML.

Recommended sampler values:

Temperature: 1 Min-P: 0.05 Top-A: 0.2 Repetition Penalty: 1.03

Recommended SillyTavern presets (via CalamitousFelicitousness):

Context Instruct and System Prompt

Training data:

Celeste 70B 0.1 data mixture minus Opus Instruct subset. See that model's card for details. Kalomaze's Opus_Instruct_25k dataset, filtered for refusals. A subset (1k rows) of ChatGPT-4o-WritingPrompts by Gryphe A subset (2k rows) of Sonnet3.5-Charcards-Roleplay by Gryphe Synthstruct and SynthRP datasets by Epiculous A subset from Dolphin-2.9.3, including filtered version of not_samantha and a small subset of systemchat.

 Training time and hardware:


  

7 hours on 8xH100 SXM, provided by FeatherlessAI

Model was created by Kearm, Auri and Cahvay.

Special thanks: to Cahvay for his work on investigating and reprocessing the corrupted dataset, removing the single biggest source of data poisoning. to FeatherlessAI for generously providing 8xH100 SXM node for training of this model to Gryphe, Lemmy, Kalomaze, Nopm, Epiculous and CognitiveComputations for the data and to Allura-org for support, feedback, beta-testing and doing quality control of EVA models.

---

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/EVA-Qwen2.5-32B-v0.2-Q5_K_M-GGUF --hf-file eva-qwen2.5-32b-v0.2-q5_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/EVA-Qwen2.5-32B-v0.2-Q5_K_M-GGUF --hf-file eva-qwen2.5-32b-v0.2-q5_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/EVA-Qwen2.5-32B-v0.2-Q5_K_M-GGUF --hf-file eva-qwen2.5-32b-v0.2-q5_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/EVA-Qwen2.5-32B-v0.2-Q5_K_M-GGUF --hf-file eva-qwen2.5-32b-v0.2-q5_k_m.gguf -c 2048