Instructions to use jayeshvpatil/tinyllama-medqa-jp-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jayeshvpatil/tinyllama-medqa-jp-v1 with Transformers:

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

pipe = pipeline("text-generation", model="jayeshvpatil/tinyllama-medqa-jp-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jayeshvpatil/tinyllama-medqa-jp-v1")
model = AutoModelForCausalLM.from_pretrained("jayeshvpatil/tinyllama-medqa-jp-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jayeshvpatil/tinyllama-medqa-jp-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jayeshvpatil/tinyllama-medqa-jp-v1

SGLang

How to use jayeshvpatil/tinyllama-medqa-jp-v1 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 "jayeshvpatil/tinyllama-medqa-jp-v1" \
    --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": "jayeshvpatil/tinyllama-medqa-jp-v1",
		"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 "jayeshvpatil/tinyllama-medqa-jp-v1" \
        --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": "jayeshvpatil/tinyllama-medqa-jp-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jayeshvpatil/tinyllama-medqa-jp-v1 with Docker Model Runner:
```
docker model run hf.co/jayeshvpatil/tinyllama-medqa-jp-v1
```

jayeshvpatil commited on Feb 6, 2024

Commit

4c52fbc

verified ·

1 Parent(s): eb906c7

Training in progress, epoch 0

Browse files

Files changed (7) hide show

adapter_model.safetensors +1 -1
runs/Feb06_21-09-16_3b97bd84572b/events.out.tfevents.1707253766.3b97bd84572b.238.0 +3 -0
runs/Feb06_21-09-52_3b97bd84572b/events.out.tfevents.1707253805.3b97bd84572b.238.1 +3 -0
runs/Feb06_21-11-48_3b97bd84572b/events.out.tfevents.1707253922.3b97bd84572b.238.2 +3 -0
runs/Feb06_21-12-11_3b97bd84572b/events.out.tfevents.1707253942.3b97bd84572b.238.3 +3 -0
runs/Feb06_21-29-15_3b97bd84572b/events.out.tfevents.1707254974.3b97bd84572b.238.4 +3 -0
training_args.bin +1 -1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab45eda4570f1f285063646a22666fba2748598db2239faaa2fd98ccbebc97d
 size 4517152

 version https://git-lfs.github.com/spec/v1
+oid sha256:8cd8671dd43f67582640f9c61ef4732caf969b942c2816b4e81c9f24fc4ec85c
 size 4517152

runs/Feb06_21-09-16_3b97bd84572b/events.out.tfevents.1707253766.3b97bd84572b.238.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:39741423c51a461ae326454690de20a39e993cc2487ccf0f830873528039623d
+size 4790

runs/Feb06_21-09-52_3b97bd84572b/events.out.tfevents.1707253805.3b97bd84572b.238.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9a703f9e74800c0e2d4e92bf54b26a433af9c3b2d9c823aa5ba96384812aa6
+size 4636

runs/Feb06_21-11-48_3b97bd84572b/events.out.tfevents.1707253922.3b97bd84572b.238.2 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cde03649dfa59e79b399efbeba5993f4414643b3e1c105aa6f8a1cb2f1da42ee
+size 4636

runs/Feb06_21-12-11_3b97bd84572b/events.out.tfevents.1707253942.3b97bd84572b.238.3 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d212c0a6f10f528c6aecf3854f5d0708102e7c02ac27229c9263f3caf92895c9
+size 8879

runs/Feb06_21-29-15_3b97bd84572b/events.out.tfevents.1707254974.3b97bd84572b.238.4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:84bafcdbca328c16528cecbe1bcebd351ab4da6f1474222b3e93ef7c7793f0bb
+size 8878

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5146a02238bc701f4b49aeb2784aa994d7851a83faae1fe4a4674bb7a36cf60e
 size 4600

 version https://git-lfs.github.com/spec/v1
+oid sha256:46957ee41f91433079c32beb1082ad050022143c3d06588af7cd2ebe03f69bc4
 size 4600