Instructions to use llmware/dragon-mistral-7b-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/dragon-mistral-7b-v0 with Transformers:

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

pipe = pipeline("text-generation", model="llmware/dragon-mistral-7b-v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/dragon-mistral-7b-v0")
model = AutoModelForCausalLM.from_pretrained("llmware/dragon-mistral-7b-v0")

llama-cpp-python

How to use llmware/dragon-mistral-7b-v0 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/dragon-mistral-7b-v0",
	filename="dragon-mistral-7b-q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use llmware/dragon-mistral-7b-v0 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/dragon-mistral-7b-v0:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf llmware/dragon-mistral-7b-v0:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/dragon-mistral-7b-v0:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf llmware/dragon-mistral-7b-v0:Q4_K_M

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 llmware/dragon-mistral-7b-v0:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf llmware/dragon-mistral-7b-v0:Q4_K_M

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 llmware/dragon-mistral-7b-v0:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/dragon-mistral-7b-v0:Q4_K_M

Use Docker

docker model run hf.co/llmware/dragon-mistral-7b-v0:Q4_K_M

LM Studio
Jan

vLLM

How to use llmware/dragon-mistral-7b-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/dragon-mistral-7b-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/dragon-mistral-7b-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/llmware/dragon-mistral-7b-v0:Q4_K_M

SGLang

How to use llmware/dragon-mistral-7b-v0 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 "llmware/dragon-mistral-7b-v0" \
    --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": "llmware/dragon-mistral-7b-v0",
		"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 "llmware/dragon-mistral-7b-v0" \
        --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": "llmware/dragon-mistral-7b-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use llmware/dragon-mistral-7b-v0 with Ollama:
```
ollama run hf.co/llmware/dragon-mistral-7b-v0:Q4_K_M
```

Unsloth Studio new

How to use llmware/dragon-mistral-7b-v0 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 llmware/dragon-mistral-7b-v0 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 llmware/dragon-mistral-7b-v0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/dragon-mistral-7b-v0 to start chatting

Docker Model Runner
How to use llmware/dragon-mistral-7b-v0 with Docker Model Runner:
```
docker model run hf.co/llmware/dragon-mistral-7b-v0:Q4_K_M
```

Lemonade

How to use llmware/dragon-mistral-7b-v0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/dragon-mistral-7b-v0:Q4_K_M

Run and chat with the model

lemonade run user.dragon-mistral-7b-v0-Q4_K_M

List all available models

lemonade list

dragon-mistral-7b-v0 / generation_test_llmware_script.py

doberst

Upload generation_test_llmware_script.py

6c80fa0 over 2 years ago

raw

history blame contribute delete

2.07 kB


	from llmware.prompts import Prompt


	def load_rag_benchmark_tester_ds():

	# pull 200 question rag benchmark test dataset from LLMWare HuggingFace repo
	from datasets import load_dataset

	ds_name = "llmware/rag_instruct_benchmark_tester"

	dataset = load_dataset(ds_name)

	print("update: loading RAG Benchmark test dataset - ", dataset)

	test_set = []
	for i, samples in enumerate(dataset["train"]):
	test_set.append(samples)

	# to view test set samples
	# print("rag benchmark dataset test samples: ", i, samples)

	return test_set


	def run_test(model_name, prompt_list):

	print("\nupdate: Starting RAG Benchmark Inference Test - ", model_name)

	# pull DRAGON / BLING model directly from catalog, e.g., no from_hf=True
	prompter = Prompt().load_model(model_name)

	for i, entries in enumerate(prompt_list):

	prompt = entries["query"]
	context = entries["context"]

	response = prompter.prompt_main(prompt,context=context,prompt_name="default_with_context", temperature=0.3)

	print("\nupdate: model inference output - ", i, response["llm_response"])
	print("update: gold_answer - ", i, entries["answer"])

	fc = prompter.evidence_check_numbers(response)
	sc = prompter.evidence_comparison_stats(response)
	sr = prompter.evidence_check_sources(response)

	print("\nFact-Checking Tools")

	for entries in fc:
	for f, facts in enumerate(entries["fact_check"]):
	print("update: fact check - ", f, facts)

	for entries in sc:
	print("update: comparison stats - ", entries["comparison_stats"])

	for entries in sr:
	for s, sources in enumerate(entries["source_review"]):
	print("update: sources - ", s, sources)

	return 0


	if __name__ == "__main__":

	core_test_set = load_rag_benchmark_tester_ds()

	# one of the 7 gpu dragon models
	gpu_model_name = "llmware/dragon-mistral-7b-v0"

	output = run_test(gpu_model_name, core_test_set)