Not-For-All-Audiences

Instructions to use Masterjp123/Mimicra-V1-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Masterjp123/Mimicra-V1-13B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Masterjp123/Mimicra-V1-13B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Masterjp123/Mimicra-V1-13B")
model = AutoModelForCausalLM.from_pretrained("Masterjp123/Mimicra-V1-13B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Masterjp123/Mimicra-V1-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Masterjp123/Mimicra-V1-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Masterjp123/Mimicra-V1-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Masterjp123/Mimicra-V1-13B

SGLang

How to use Masterjp123/Mimicra-V1-13B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Masterjp123/Mimicra-V1-13B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Masterjp123/Mimicra-V1-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Masterjp123/Mimicra-V1-13B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Masterjp123/Mimicra-V1-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Masterjp123/Mimicra-V1-13B with Docker Model Runner:
```
docker model run hf.co/Masterjp123/Mimicra-V1-13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mimicra - A test LLM made possible by: ModelREVOLVER

NOTE: I am classifying this merge as a fail. becuase It has too many flaws.

Perpose of this Model:

This Model was selectivly Merged with Models I have made through Merging, Models with high rankings And Models I liked using to make a ultimatly great model; Which is Good at RP, uncensored, Smart and creative

Quants:

GGUF

Currently no other Quants

Model Parts:

Magdump-13b RP Model

ZettaPi-13B RP Model

genz-13b-v2 Has Good score on LLM leader board

Unholy-v1.1-13B RP Model with... Unholy resonces...

Thespis-13b-v0.5 RP Model but with emojis

UtopiaXL-13B Interesting model bc Utopia was a good model

rpguild-chatml-13b Rp Model

Echidna-13b-v0.3 Rp Model

CodeLlama-13B-RP-2 RP Model basic on Code Llama which makes it interesting

Augmental-13b-v1.50_B RP Model based on MithosMax

IkariDev_Athnete-13B Seemed nice when I tried it

MasterRP-V1-L2-13B My own model meant for RP But It was not Very Good

Hesperus-v1-13B-L2-fp16 Very Interesting Model bc it has a lot of Training data and plus it just seems interesting

l2-13b-thespurral-m2.2 RP Model But unique by acting differently than most

Methodolgy

By Mixing together models with the best inteligence and Proformence, to get a model with Great Proformence and Inteligence.

Prompt template:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Downloads last month: 18

Safetensors

Model size

13B params

Tensor type

F16

Model tree for Masterjp123/Mimicra-V1-13B

Quantizations

1 model