Instructions to use DatPySci/tiny-llama-kto-iter0-0.1-epoch1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DatPySci/tiny-llama-kto-iter0-0.1-epoch1 with Transformers:

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

pipe = pipeline("text-generation", model="DatPySci/tiny-llama-kto-iter0-0.1-epoch1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DatPySci/tiny-llama-kto-iter0-0.1-epoch1")
model = AutoModelForCausalLM.from_pretrained("DatPySci/tiny-llama-kto-iter0-0.1-epoch1")
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 DatPySci/tiny-llama-kto-iter0-0.1-epoch1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DatPySci/tiny-llama-kto-iter0-0.1-epoch1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DatPySci/tiny-llama-kto-iter0-0.1-epoch1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DatPySci/tiny-llama-kto-iter0-0.1-epoch1

SGLang

How to use DatPySci/tiny-llama-kto-iter0-0.1-epoch1 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 "DatPySci/tiny-llama-kto-iter0-0.1-epoch1" \
    --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": "DatPySci/tiny-llama-kto-iter0-0.1-epoch1",
		"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 "DatPySci/tiny-llama-kto-iter0-0.1-epoch1" \
        --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": "DatPySci/tiny-llama-kto-iter0-0.1-epoch1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DatPySci/tiny-llama-kto-iter0-0.1-epoch1 with Docker Model Runner:
```
docker model run hf.co/DatPySci/tiny-llama-kto-iter0-0.1-epoch1
```

DatPySci commited on Mar 9, 2024

Commit

00f3d6b

verified ·

1 Parent(s): 65f2b24

Training in progress, step 200

Browse files

Files changed (2) hide show

model.safetensors +1 -1
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed0bfd23635fa5ed9ffb434d7b5a9d03c39fa32d230e2b8d5640121ae6fd6ed
 size 2200119864

 version https://git-lfs.github.com/spec/v1
+oid sha256:bab7e11ff61607d6cf5c8033dd6df7c318b906962348042eab0dc106a6e2cf31
 size 2200119864

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0ece2b2aa3c70d42a4f0d6c694a85c98bf76b53746a4e6391839a19a6ff0c8
 size 6200

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1d8e54dd54f07591f7f0828efa59831fa5364d3723b5d6cd487b08bc38c9d61
 size 6200