Instructions to use jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser with Transformers:

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

pipe = pipeline("text-generation", model="jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser")
model = AutoModelForCausalLM.from_pretrained("jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser

SGLang

How to use jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser 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 "jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser" \
    --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": "jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser",
		"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 "jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser" \
        --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": "jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser with Docker Model Runner:
```
docker model run hf.co/jtatman/Reyna-Mini-1.8B-v0.2-function-call-laser
```

jtatman commited on Feb 23, 2024

Commit

2de4cf0

verified ·

1 Parent(s): 8976355

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -22,10 +22,10 @@ As Aloobun's model is well performing and impressive on it's own, I decided to a
 ### Direct Use
-Chat
-Conversational
-Text Generation
-Function Calling
 ## Bias, Risks, and Limitations
@@ -62,9 +62,11 @@ Use at your own risk. It's a great small model, owing to the base model before t
 ### Training Procedure
 [LaserRMT](https://github.com/cognitivecomputations/laserRMT) was used to refine the weights, using the 16 highest scored weights specifically by noise-to-ratio analysis.
 This technique avoids training unnecessarily low-performng weights that can turn to garbage. By pruning these weights, the model size is decreased slightly.
 ![axolotl](https://github.com/OpenAccess-AI-Collective/axolotl/blob/main/image/axolotl-badge-web.png?raw=true)
 Axolotl was used for training and dataset tokenization.
 #### Preprocessing [optional]

 ### Direct Use
+- Chat
+- Conversational
+- Text Generation
+- Function Calling
 ## Bias, Risks, and Limitations
 ### Training Procedure
 [LaserRMT](https://github.com/cognitivecomputations/laserRMT) was used to refine the weights, using the 16 highest scored weights specifically by noise-to-ratio analysis.
 This technique avoids training unnecessarily low-performng weights that can turn to garbage. By pruning these weights, the model size is decreased slightly.
 ![axolotl](https://github.com/OpenAccess-AI-Collective/axolotl/blob/main/image/axolotl-badge-web.png?raw=true)
 Axolotl was used for training and dataset tokenization.
 #### Preprocessing [optional]