Instructions to use Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B with Transformers:

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

pipe = pipeline("text-generation", model="Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B")
model = AutoModelForCausalLM.from_pretrained("Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B

SGLang

How to use Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B 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 "Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B with Docker Model Runner:
```
docker model run hf.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Image by ろ47

Merge

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

Merge Details

The goal of this merge was to make an RP model better suited for role-plays with heavy themes such as but not limited to:

Mental illness
Self-harm
Trauma
Suicide

I hated how RP models tended to be overly positive and hopeful with role-plays involving such themes, but thanks to failspy/Llama-3-8B-Instruct-MopeyMule this problem has been lessened considerably.

If you're an enjoyer of savior/reverse savior type role-plays like myself, then this model is for you.

Usage Info

This model is meant to be used with asterisks/quotes RPing formats, any other format that isn't asterisks/quotes is likely to cause issues

Quants

Weighted GGUFs by mradermacher
Static GGUFs by mradermacher

Models Merged

The following models were included in the merge:

Secret Sauce

The following YAML configurations were used to produce this model:

Umbral-Mind-1-pt.1

models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
  - model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B
    parameters:
      density: 0.5
      weight: [0.33, 0.0825, 0.0825, 0.0825, 0.0825]
  - model: tannedbum/L3-Nymeria-Maid-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.33, 0.0825, 0.0825, 0.0825]
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.33, 0.0825, 0.0825]
  - model: tannedbum/L3-Nymeria-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.0825, 0.33, 0.0825]
  - model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.0825, 0.0825, 0.33]
merge_method: dare_ties
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Umbral-Mind-1-pt.2

models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
  - model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.0825, 0.0825, 0.33]
  - model: tannedbum/L3-Nymeria-Maid-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.0825, 0.33, 0.0825]
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.33, 0.0825, 0.0825]
  - model: tannedbum/L3-Nymeria-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.33, 0.0825, 0.0825, 0.0825]
  - model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.33, 0.0825, 0.0825, 0.0825, 0.0825]
merge_method: breadcrumbs_ties
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Umbral-Mind-1

models:
  - model: Casual-Autopsy/Umbral-Mind-1-pt.1
  - model: Casual-Autopsy/Umbral-Mind-1-pt.2
merge_method: slerp
base_model: Casual-Autopsy/Umbral-Mind-1-pt.1
parameters:
  t:
    - filter: self_attn
      value: [0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5]
    - filter: mlp
      value: [0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5]
    - value: 0.5
dtype: bfloat16

Umbral-Mind-2-pt.1

models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
  - model: Cas-Warehouse/Llama-3-Mopeyfied-Psychology-v2
    parameters:
      density: 0.5
      weight: [0.33, 0.0825, 0.0825, 0.0825, 0.0825]
  - model: migtissera/Llama-3-8B-Synthia-v3.5
    parameters:
      density: 0.5
      weight: [0.0825, 0.33, 0.0825, 0.0825, 0.0825]
  - model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.33, 0.0825, 0.0825]
  - model: v000000/L3-8B-Poppy-Sunspice
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.0825, 0.33, 0.0825]
  - model: Cas-Warehouse/Llama-3-Mopeyfied-Psychology-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.0825, 0.0825, 0.33]
merge_method: dare_ties
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Umbral-Mind-2-pt.2

models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
  - model: Cas-Warehouse/Llama-3-Mopeyfied-Psychology-v2
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.0825, 0.0825, 0.33]
  - model: migtissera/Llama-3-8B-Synthia-v3.5
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.0825, 0.33, 0.0825]
  - model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.33, 0.0825, 0.0825]
  - model: Magpie-Align/Llama-3-8B-WizardLM-196K
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.33, 0.0825, 0.0825, 0.0825]
  - model: Cas-Warehouse/Llama-3-Mopeyfied-Psychology-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.33, 0.0825, 0.0825, 0.0825, 0.0825]
merge_method: breadcrumbs_ties
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Umbral-Mind-2

models:
  - model: Casual-Autopsy/Umbral-Mind-2-pt.1
  - model: Casual-Autopsy/Umbral-Mind-2-pt.2
merge_method: slerp
base_model: Casual-Autopsy/Umbral-Mind-2-pt.1
parameters:
  t:
    - filter: self_attn
      value: [0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5]
    - filter: mlp
      value: [0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5]
    - value: 0.5
dtype: bfloat16

Umbral-Mind-3-pt.1

models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
  - model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-8B
    parameters:
      density: 0.5
      weight: [0.33, 0.0825, 0.0825, 0.0825, 0.0825]
  - model: invisietch/EtherealRainbow-v0.3-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.33, 0.0825, 0.0825, 0.0825]
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.33, 0.0825, 0.0825]
  - model: crestf411/L3-8B-sunfall-v0.4-stheno-v3.2
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.0825, 0.33, 0.0825]
  - model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B
    parameters:
      density: 0.5
      weight: [0.0825, 0.0825, 0.0825, 0.0825, 0.33]
merge_method: dare_ties
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Umbral-Mind-3-pt.2

models:
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
  - model: Cas-Warehouse/Llama-3-SOVL-MopeyMule-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.0825, 0.0825, 0.33]
  - model: invisietch/EtherealRainbow-v0.3-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.0825, 0.33, 0.0825]
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.0825, 0.33, 0.0825, 0.0825]
  - model: crestf411/L3-8B-sunfall-v0.4-stheno-v3.2
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.0825, 0.33, 0.0825, 0.0825, 0.0825]
  - model: Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B
    parameters:
      gamma: 0.01
      density: 0.9
      weight: [0.33, 0.0825, 0.0825, 0.0825, 0.0825]
merge_method: breadcrumbs_ties
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Umbral-Mind-3

models:
  - model: Casual-Autopsy/Umbral-Mind-3-pt.1
  - model: Casual-Autopsy/Umbral-Mind-3-pt.2
merge_method: slerp
base_model: Casual-Autopsy/Umbral-Mind-3-pt.1
parameters:
  t:
    - filter: self_attn
      value: [0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5]
    - filter: mlp
      value: [0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5, 0.7, 0.3, 0.5, 0.3, 0.7, 0.5]
    - value: 0.5
dtype: bfloat16

Umbral-Mind-4

models:
  - model: Casual-Autopsy/Umbral-Mind-1
  - model: Casual-Autopsy/Umbral-Mind-3
merge_method: slerp
base_model: Casual-Autopsy/Umbral-Mind-1
parameters:
  t:
    - value: [0.1, 0.15, 0.2, 0.4, 0.6, 0.4, 0.2, 0.15, 0.1]
dtype: bfloat16

Umbral-Mind-5

models:
  - model: Casual-Autopsy/Umbral-Mind-4
  - model: Casual-Autopsy/Umbral-Mind-2
merge_method: slerp
base_model: Casual-Autopsy/Umbral-Mind-4
parameters:
  t:
    - value: [0.7, 0.5, 0.3, 0.25, 0.2, 0.25, 0.3, 0.5, 0.7]
  embed_slerp: true
dtype: bfloat16

Umbral-Mind-6

models:
  - model: mergekit-community/Umbral-Mind-5
  - model: Casual-Autopsy/Mopey-Omelette
merge_method: slerp
base_model: mergekit-community/Umbral-Mind-5
parameters:
  t:
    - value: [0.2, 0.25, 0.3, 0.4, 0.3, 0.25, 0.2, 0.25, 0.3, 0.4, 0.3, 0.25, 0.2]
  embed_slerp: true
dtype: bfloat16

Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B

models:
  - model: Casual-Autopsy/Umbral-Mind-6
  - model: aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-32K
    parameters:
      weight: [0.02, -0.01, -0.01, 0.02]
  - model: ResplendentAI/Nymph_8B
    parameters:
      weight: [-0.01, 0.02, 0.02, -0.01]
  - model: ChaoticNeutrals/Poppy_Porpoise-1.0-L3-8B
    parameters:
      weight: [-0.01, 0.02, 0.02, -0.01]
  - model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
    parameters:
      weight: [0.02, -0.01, -0.01, 0.02]
merge_method: task_arithmetic
base_model: Casual-Autopsy/Umbral-Mind-6
parameters:
  normalize: false
dtype: bfloat16