Instructions to use kcherry497/dyno-blast-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kcherry497/dyno-blast-4b with Transformers:

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

pipe = pipeline("text-generation", model="kcherry497/dyno-blast-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kcherry497/dyno-blast-4b")
model = AutoModelForMultimodalLM.from_pretrained("kcherry497/dyno-blast-4b")
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]:]))

llama-cpp-python

How to use kcherry497/dyno-blast-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kcherry497/dyno-blast-4b",
	filename="dyno-blast-4b-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kcherry497/dyno-blast-4b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kcherry497/dyno-blast-4b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf kcherry497/dyno-blast-4b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kcherry497/dyno-blast-4b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf kcherry497/dyno-blast-4b:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kcherry497/dyno-blast-4b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf kcherry497/dyno-blast-4b:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kcherry497/dyno-blast-4b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kcherry497/dyno-blast-4b:Q8_0

Use Docker

docker model run hf.co/kcherry497/dyno-blast-4b:Q8_0

LM Studio
Jan

vLLM

How to use kcherry497/dyno-blast-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kcherry497/dyno-blast-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kcherry497/dyno-blast-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kcherry497/dyno-blast-4b:Q8_0

SGLang

How to use kcherry497/dyno-blast-4b 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 "kcherry497/dyno-blast-4b" \
    --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": "kcherry497/dyno-blast-4b",
		"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 "kcherry497/dyno-blast-4b" \
        --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": "kcherry497/dyno-blast-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use kcherry497/dyno-blast-4b with Ollama:
```
ollama run hf.co/kcherry497/dyno-blast-4b:Q8_0
```

Unsloth Studio

How to use kcherry497/dyno-blast-4b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kcherry497/dyno-blast-4b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kcherry497/dyno-blast-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kcherry497/dyno-blast-4b to start chatting

How to use kcherry497/dyno-blast-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf kcherry497/dyno-blast-4b:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kcherry497/dyno-blast-4b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use kcherry497/dyno-blast-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf kcherry497/dyno-blast-4b:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default kcherry497/dyno-blast-4b:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use kcherry497/dyno-blast-4b with Docker Model Runner:
```
docker model run hf.co/kcherry497/dyno-blast-4b:Q8_0
```

Lemonade

How to use kcherry497/dyno-blast-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kcherry497/dyno-blast-4b:Q8_0

Run and chat with the model

lemonade run user.dyno-blast-4b-Q8_0

List all available models

lemonade list

dyno-blast-4b

A QLoRA fine-tune of Qwen3-4B that answers blasting / explosives technical and safety questions strictly from retrieved context, attaches [N] + page citations to every claim, and refuses when the answer isn't in the provided sources.

This is the generation half of a grounded RAG system over Dyno Nobel Australia's public technical literature (product technical data sheets, Safety Data Sheets, application guides, case studies). Facts live in the retriever; the model learns the behavior — cite, ground, refuse. Companion vector DB: kcherry497/dyno-blast-4b-rag.

Intended use & limitations

Retrieval-augmented Q&A for mining / quarry / blasting professionals. Not a standalone knowledge source — use with the retriever (intfloat/e5-base-v2 + a Qdrant collection). For SDS / safety content, always verify against the cited source PDF; the model is trained to give page numbers for exactly this reason. Domain-specific to Dyno Nobel AU products.

Training

Base: Qwen/Qwen3-4B
Method: QLoRA (4-bit nf4), r=16, α=32, dropout=0.05, targets all attn + MLP projections
Data: 1,674 synthetic grounded examples — 1,656 [N]-cited answers + 18 refusal / safe-decline examples — generated by a teacher over retrieved context, covering SDS sections, technical specs, application/case-study/brochure topics, Explosive Engineers Guide articles, industrial chemicals, and blast calculators
Schedule: 3 epochs, lr 1e-4 cosine, full-sequence SFT
Result: final train_loss 0.97

Retrieval corpus (companion dataset repo): 3,819 chunks across 682 documents — dynonobel.com.au + dynonobel.com (126 products) + the Explosive Engineers Guide app (4 regions) + Industrial Chemicals + resource-centre case studies/guides/brochures + blast calculators.

Files

*.safetensors — merged fp16 weights (load with transformers)
dyno-blast-4b-q8_0.gguf — q8_0 GGUF for llama.cpp / Ollama

Prompt format

Grounded system prompt (answer only from numbered SOURCEs, cite [N], refuse if absent) + numbered SOURCE [N] blocks from the retriever, then the question. The exact system prompt and chunk schema are in the companion dataset repo.

Downloads last month: 275

Safetensors

Model size

4B params

Tensor type

F16

Model tree for kcherry497/dyno-blast-4b

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(231)

this model

Quantizations

1 model