Instructions to use TroyDoesAI/MermaidLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/MermaidLlama with Transformers:

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

pipe = pipeline("text-generation", model="TroyDoesAI/MermaidLlama")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TroyDoesAI/MermaidLlama")
model = AutoModelForCausalLM.from_pretrained("TroyDoesAI/MermaidLlama")
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 TroyDoesAI/MermaidLlama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TroyDoesAI/MermaidLlama

SGLang

How to use TroyDoesAI/MermaidLlama 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 "TroyDoesAI/MermaidLlama" \
    --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": "TroyDoesAI/MermaidLlama",
		"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 "TroyDoesAI/MermaidLlama" \
        --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": "TroyDoesAI/MermaidLlama",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TroyDoesAI/MermaidLlama with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/MermaidLlama
```

TroyDoesAI commited on Jan 16, 2024

Commit

aa704ca

verified ·

1 Parent(s): 1247e82

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -65,39 +65,39 @@ Exciting times ahead as we delve into the MermaidLLama revolution! 🚀
 LoRA Rank
 Also called dimension count. Higher values = larger file, more content control. Smaller values = smaller file, less control. Use 4 or 8 for style, 128 or 256 to teach, 1024+ for fine-detail on big data. More VRAM is needed for higher ranks.
-2048
 LoRA Alpha
 This divided by the rank becomes the scaling of the LoRA. Higher means stronger. A good standard value is twice your Rank.
-4096
 Batch Size
 Global batch size. The two batch sizes together determine gradient accumulation (gradientAccum = batch / microBatch). Higher gradient accum values lead to better quality training.
-1
 Micro Batch Size
 Per-device batch size (NOTE: multiple devices not yet implemented). Increasing this will increase VRAM usage.
-1
 Cutoff Length
 Cutoff length for text input. Essentially, how long of a line of text to feed in at a time. Higher values require drastically more VRAM.
-4096
 Save every n steps
 If above 0, a checkpoint of the LoRA will be saved every time this many steps pass.
-1000
 Epochs
 Number of times every entry in the dataset should be fed into training. So 1 means feed each item in once, 5 means feed it in five times, etc.
-3
 Learning Rate
 In scientific notation.
-1e-6
 LR Scheduler
 Learning rate scheduler - defines how the learning rate changes over time. "Constant" means never change, "linear" means to go in a straight line from the learning rate down to 0, cosine follows a curve, etc.
-cosine
 Target Modules

 LoRA Rank
 Also called dimension count. Higher values = larger file, more content control. Smaller values = smaller file, less control. Use 4 or 8 for style, 128 or 256 to teach, 1024+ for fine-detail on big data. More VRAM is needed for higher ranks.
+- 2048
 LoRA Alpha
 This divided by the rank becomes the scaling of the LoRA. Higher means stronger. A good standard value is twice your Rank.
+- 4096
 Batch Size
 Global batch size. The two batch sizes together determine gradient accumulation (gradientAccum = batch / microBatch). Higher gradient accum values lead to better quality training.
+- 1
 Micro Batch Size
 Per-device batch size (NOTE: multiple devices not yet implemented). Increasing this will increase VRAM usage.
+- 1
 Cutoff Length
 Cutoff length for text input. Essentially, how long of a line of text to feed in at a time. Higher values require drastically more VRAM.
+- 4096
 Save every n steps
 If above 0, a checkpoint of the LoRA will be saved every time this many steps pass.
+- 1000
 Epochs
 Number of times every entry in the dataset should be fed into training. So 1 means feed each item in once, 5 means feed it in five times, etc.
+- 3
 Learning Rate
 In scientific notation.
+- 1e-6
 LR Scheduler
 Learning rate scheduler - defines how the learning rate changes over time. "Constant" means never change, "linear" means to go in a straight line from the learning rate down to 0, cosine follows a curve, etc.
+- cosine
 Target Modules