---
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
datasets:
- PocketDoc/Dans-Prosemaxx-Cowriter-3-S
- PocketDoc/Dans-Prosemaxx-Adventure
- PocketDoc/Dans-Failuremaxx-Adventure-3
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot
- PocketDoc/Dans-Prosemaxx-InstructWriter-Continue
- PocketDoc/Dans-Personamaxx-VN
- PocketDoc/Dans-Personamaxx
- PocketDoc/Dans-Personamaxx-Rainy
- PocketDoc/Dans-Personamaxx-C1
language:
- en
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---

# Triangle104/Dans-SakuraKaze-V1.0.0-12b-Q8_0-GGUF
This model was converted to GGUF format from [`PocketDoc/Dans-SakuraKaze-V1.0.0-12b`](https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b) 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/PocketDoc/Dans-SakuraKaze-V1.0.0-12b) for more details on the model.

---
A model based on Dans-PersonalityEngine-V1.1.0-12b with a focus on character RP, visual novel style group chats, old school text adventures, and co-writing.

Key Details
-
BASE MODEL: PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
LICENSE: apache-2.0
LANGUAGE: English
CONTEXT LENGTH: 32768 tokens

Sponsored by Chub.AI

Recommended Settings
-
TEMPERATURE: 1.0
TOP_P: 0.95
MIN_P: 0.05

Prompting Format
-
The model uses standard "ChatML" format:

<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>

SillyTavern Templates
-
Context Template
-
{
    "story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>\n",
    "example_separator": "",
    "chat_start": "",
    "use_stop_strings": false,
    "allow_jailbreak": false,
    "always_force_name2": false,
    "trim_sentences": false,
    "include_newline": false,
    "single_line": false,
    "name": "Dan-ChatML"
}

Instruct Template
-
{
    "system_prompt": "Write {{char}}'s actions and dialogue, user will write {{user}}'s.",
    "input_sequence": "<|im_start|>user\n",
    "output_sequence": "<|im_start|>assistant\n",
    "first_output_sequence": "",
    "last_output_sequence": "",
    "system_sequence_prefix": "",
    "system_sequence_suffix": "",
    "stop_sequence": "<|im_end|>",
    "wrap": false,
    "macro": true,
    "names": false,
    "names_force_groups": false,
    "activation_regex": "",
    "skip_examples": false,
    "output_suffix": "<|im_end|>\n",
    "input_suffix": "<|im_end|>\n",
    "system_sequence": "<|im_start|>system\n",
    "system_suffix": "<|im_end|>\n",
    "user_alignment_message": "",
    "last_system_sequence": "",
    "system_same_as_user": false,
    "first_input_sequence": "",
    "last_input_sequence": "",
    "name": "Dan-ChatML"
}

A Chub.AI Sponsored Model

Sponsored by Chub.AI

Character Hub supported this model with 45 hours on a 2x A100 80GB system. This is only some of what they've provided me for training and I am very grateful for their contributions.

Character Hub has been supporting model development for quite a while now and they may be interested in your projects! Contact them through this google form.

Support Development
-
Development is limited by funding and resources. To help support:

- Contact on HF

- Email: visuallyadequate@gmail.com


---
## 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/Dans-SakuraKaze-V1.0.0-12b-Q8_0-GGUF --hf-file dans-sakurakaze-v1.0.0-12b-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/Dans-SakuraKaze-V1.0.0-12b-Q8_0-GGUF --hf-file dans-sakurakaze-v1.0.0-12b-q8_0.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/Dans-SakuraKaze-V1.0.0-12b-Q8_0-GGUF --hf-file dans-sakurakaze-v1.0.0-12b-q8_0.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/Dans-SakuraKaze-V1.0.0-12b-Q8_0-GGUF --hf-file dans-sakurakaze-v1.0.0-12b-q8_0.gguf -c 2048
```