Instructions to use grimjim/fireblossom-32K-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/fireblossom-32K-7B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/fireblossom-32K-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/fireblossom-32K-7B")
model = AutoModelForCausalLM.from_pretrained("grimjim/fireblossom-32K-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use grimjim/fireblossom-32K-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/fireblossom-32K-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/fireblossom-32K-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimjim/fireblossom-32K-7B

SGLang

How to use grimjim/fireblossom-32K-7B 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/fireblossom-32K-7B" \
    --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/fireblossom-32K-7B",
		"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/fireblossom-32K-7B" \
        --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/fireblossom-32K-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimjim/fireblossom-32K-7B with Docker Model Runner:
```
docker model run hf.co/grimjim/fireblossom-32K-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Fireblossom-32K-7B

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

For this merge, I went back to Mistral 7B v0.1 for the literal base model for task arithmetic merger, which can be pushed to at least 16K context length after adjusting rope theta from 10K to 100K. With the original (true) base model, the models merged in should be mathematically equivalent to LoRA adapters. I left the original 32K context claimed by Mistral 7B v0.1.

The goal was a merge model more varied in its outputs, a goal which inherently harms accuracy in favor of creativity. To this end, I chose a model trained to be strong at narrative roleplay (cgato's work) along with three models that were good at reasoning (fine-tunes by HuggingFaceH4 and SanjiWatsuki). The result appears to be good at following card instructions, perhaps to a fault.

Sampler settings: Tested lightly with temperature=0.7 and minP=0.01. For greater creativity, boost temperature.

Prompts: Alpaca format natively supported, although ChatML was used during testing.

Download options:

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
    parameters:
      weight: 0.45
  - model: cgato/TheSpice-7b-v0.1.1
    parameters:
      weight: 0.05
  - model: HuggingFaceH4/zephyr-7b-beta
    parameters:
      weight: 0.05
  - model: SanjiWatsuki/Kunoichi-7B
    parameters:
      weight: 0.45
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
dtype: float16