README.md

---
library_name: transformers
tags:
- not-for-all-audiences
- mergekit
- llama-cpp
- gguf-my-repo
datasets:
- crestf411/LimaRP-DS
- Gryphe/Sonnet3.5-Charcard-Roleplay
- anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system
- anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
- anthracite-org/kalo-opus-instruct-3k-filtered-no-system
- anthracite-org/nopm_claude_writing_fixed
base_model: crestf411/Q2.5-32B-Slush
---

# Triangle104/Q2.5-32B-Slush-Q6_K-GGUF
This model was converted to GGUF format from [`crestf411/Q2.5-32B-Slush`](https://huggingface.co/crestf411/Q2.5-32B-Slush) 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/crestf411/Q2.5-32B-Slush) for more details on the model.

---
Model details:
-
Slush is a two-stage model trained with high LoRA dropout, where stage 1 is a pretraining continuation on the base model, aimed at boosting the model's creativity and writing capabilities. This is then merged into the instruction tune model, and stage 2 is a fine tuning step on top of this to further enhance its roleplaying capabilities and/or to repair any damage caused in the stage 1 merge.

This is still early stage. As always, feedback is welcome, and begone if you demand perfection.

The second stage, like the Sunfall series, follows the Silly Tavern preset (ChatML), so ymmv in particular if you use some other tool and/or preset.
Parameter suggestions

I did all my testing with temp 1, min-p 0.1, DRY 0.8, but enabled XTC as context grew and/or the model started saying "the same stuff".

Qwen 2.5 32B Instruct (vanilla) has a strong tendency to start speaking for the user, especially in narrator scenarios. I was unable to properly train this out of the model completely, so you may want to add e.g. "\nYou" as a stopping string, and enable "trim incomplete sentences", especially if you have banned sentences.

The model has a tendency to add an unnecesary final paragraph to responses during roleplay, sort of like a "summary" of how the character is feeling. Keeping it is OK, but it may snowball quickly. Hoping to address this but not sure how.
Training details

    Stage 1 (continued pretraining)
        Target: Qwen/Qwen2.5-32B (resulting LoRA merged into Qwen/Qwen2.5-32B-Instruct)
        LoRA dropout 0.5 (motivation)
        LoRA rank 32, alpha 64 (motivation)
        LR cosine 4e-6
        LoRA+ with LR Ratio: 15
        Context size: 8192
        Gradient accumulation steps: 4
        Epochs: 1
    Stage 2 (fine tune)
        Target: Stage 1 model
        LoRA dropout 0.5
        LoRA rank 32, alpha 64
        LR cosine 5e-6 (min 5e-7)
        LoRA+ with LR Ratio: 15
        Context size: 16384
        Gradient accumulation steps: 4
        Epochs: 1

Merge Details
Merge Method

This model was merged using the TIES merge method.
Configuration

The following YAML configuration was used to produce this model:

models:
  - model: stage1-model
    parameters:
      weight: 1
      density: 1
  - model: stage2-model
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-32B-Instruct
    parameters:
      weight: 0.9
      density: 0.9
merge_method: ties
base_model: Qwen/Qwen2.5-32B
parameters:
  weight: 0.9
  density: 0.9
  normalize: true
  int8_mask: true
tokenizer_source: Qwen/Qwen2.5-32B-Instruct
dtype: bfloat16

---
## 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/Q2.5-32B-Slush-Q6_K-GGUF --hf-file q2.5-32b-slush-q6_k.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/Q2.5-32B-Slush-Q6_K-GGUF --hf-file q2.5-32b-slush-q6_k.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/Q2.5-32B-Slush-Q6_K-GGUF --hf-file q2.5-32b-slush-q6_k.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/Q2.5-32B-Slush-Q6_K-GGUF --hf-file q2.5-32b-slush-q6_k.gguf -c 2048
```