Instructions to use grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3 with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3")
model = AutoModelForCausalLM.from_pretrained("grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3

SGLang

How to use grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3 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 "grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3" \
    --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": "grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3",
		"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 "grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3" \
        --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": "grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3 with Docker Model Runner:
```
docker model run hf.co/grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3
```

Modicum-of-Doubt-v1-24B-4bpw-h6-exl3

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

Exllamav3 was used to create a quant at 4bpw with h6. With 16GB VRAM, it's possible to run 16K context at fp16 with some room to spare.

The model vision component was excised from all merge contributions.

Creative text generation outputs seem to trend toward the short side, sometimes to the point of feeling choppy, hence the model name. This model is not the most stellar, but the result is interesting, going against the individual tendency of the two contributing models toward longer outputs.

Tested sampler settings: temperature 1.0, minP 0.02

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using mrfakename/mistral-small-3.1-24b-base-2503-hf as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: mrfakename/mistral-small-3.1-24b-base-2503-hf
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: true
models:
  - model: mrfakename/mistral-small-3.1-24b-base-2503-hf
  - model: Doctor-Shotgun/MS3.2-24B-Magnum-Diamond
    parameters:
      weight: 0.5
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
    parameters:
      weight: 0.5

Downloads last month: 5

Safetensors

Model size

6B params

Tensor type

F16

I16

Model tree for grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3

Base model

grimjim/Modicum-of-Doubt-v1-24B

Quantized

(4)

this model

Paper for grimjim/Modicum-of-Doubt-v1-24B-4bpw-h6-exl3

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 9