Instructions to use FlareRebellion/WeirdCompound-v1.2-24b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlareRebellion/WeirdCompound-v1.2-24b with Transformers:

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

pipe = pipeline("text-generation", model="FlareRebellion/WeirdCompound-v1.2-24b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlareRebellion/WeirdCompound-v1.2-24b")
model = AutoModelForCausalLM.from_pretrained("FlareRebellion/WeirdCompound-v1.2-24b")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FlareRebellion/WeirdCompound-v1.2-24b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlareRebellion/WeirdCompound-v1.2-24b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlareRebellion/WeirdCompound-v1.2-24b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlareRebellion/WeirdCompound-v1.2-24b

SGLang

How to use FlareRebellion/WeirdCompound-v1.2-24b 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 "FlareRebellion/WeirdCompound-v1.2-24b" \
    --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": "FlareRebellion/WeirdCompound-v1.2-24b",
		"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 "FlareRebellion/WeirdCompound-v1.2-24b" \
        --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": "FlareRebellion/WeirdCompound-v1.2-24b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlareRebellion/WeirdCompound-v1.2-24b with Docker Model Runner:
```
docker model run hf.co/FlareRebellion/WeirdCompound-v1.2-24b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

WeirdCompound-v1.2-24b

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

Merge Details

Notes

This is a multi-stage merge. There's little method to my madness and I just stopped when I arrived at something that I liked.

Starting point was DepravedCartographer-v1.0-24b with slight changes.

Mistral released 3.2 2506, so I wanted to see how these slerp merges would turn out with it in the tree, even if none of the other models is a strict descendant of Mistral 3.2. Seems to be coherent enough, so I'm uploading this. No clue how many of the 3.2 improvements survived the process though.

Changelog

v1.1

/intermediate/model/B: replaced anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF with anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML

v1.2

/intermediate/model/B: replaced anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML with anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only for default tokenizer config.

Merge Method

This model was merged using the Model Stock merge method using TheDrummer/Cydonia-24B-v3 as a base.

This model was merged using the SLERP merge method.

This model was merged using the NuSLERP merge method using /intermediate/model/B as a base.

Models Merged

The following models were included in the merge:

Delta-Vector/Austral-24B-Winton
Doctor-Shotgun/MS3.1-24B-Magnum-Diamond
aixonlab/Eurydice-24b-v3.5
PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
/intermediate/model/A
/intermediate/model/B
/intermediate/model/C

Configuration

The following YAML configuration was used to produce this model:

base_model: TheDrummer/Cydonia-24B-v3 # Cydonia v3
merge_method: model_stock
dtype: bfloat16
models:
  - model: aixonlab/Eurydice-24b-v3.5 # storytelling / RP
  - model: TheDrummer/Cydonia-24B-v3 # sprinkle in some extra Cydonia v3
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b # Prompt Adherence
  - model: Delta-Vector/Austral-24B-Winton  # Adventure
  - model: Doctor-Shotgun/MS3.1-24B-Magnum-Diamond # claude opus

→ /intermediate/model/A →

merge_method: slerp
dtype: bfloat16
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
models:
  - model: /intermediate/model/A
parameters:
  t: 0.4

→ /intermediate/model/B →

merge_method: nuslerp
dtype: bfloat16
base_model: /intermediate/model/B
models:
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
    parameters:
      weight: 0.6
  - model: aixonlab/Eurydice-24b-v3.5
    parameters:
      weight: 0.4

→ /intermediate/model/C →

merge_method: slerp
dtype: bfloat16
base_model: /intermediate/model/B
models:
  - model: /intermediate/model/C
parameters:
  t: 0.5

→ WeirdCompound-v1.2-24b

Downloads last month: 6

Safetensors

Model size

24B params

Tensor type

BF16

Model tree for FlareRebellion/WeirdCompound-v1.2-24b

Quantizations

3 models

Paper for FlareRebellion/WeirdCompound-v1.2-24b

Model Stock: All we need is just a few fine-tuned models

Paper • 2403.19522 • Published Mar 28, 2024 • 15