Instructions to use ariG23498/tiny-llama3-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ariG23498/tiny-llama3-test with Transformers:

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

pipe = pipeline("text-generation", model="ariG23498/tiny-llama3-test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ariG23498/tiny-llama3-test")
model = AutoModelForCausalLM.from_pretrained("ariG23498/tiny-llama3-test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ariG23498/tiny-llama3-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ariG23498/tiny-llama3-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ariG23498/tiny-llama3-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ariG23498/tiny-llama3-test

SGLang

How to use ariG23498/tiny-llama3-test 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 "ariG23498/tiny-llama3-test" \
    --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": "ariG23498/tiny-llama3-test",
		"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 "ariG23498/tiny-llama3-test" \
        --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": "ariG23498/tiny-llama3-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ariG23498/tiny-llama3-test with Docker Model Runner:
```
docker model run hf.co/ariG23498/tiny-llama3-test
```

ariG23498 HF Staff commited on Jun 24, 2024

Commit

3a52438

verified ·

1 Parent(s): e2e605d

Upload LlamaForCausalLM

Browse files

Files changed (5) hide show

config.json +1 -1
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +2 -2
model-00003-of-00003.safetensors +1 -1
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -9,7 +9,7 @@
   "hidden_act": "silu",
   "hidden_size": 32,
   "initializer_range": 0.02,
-  "intermediate_size": 32,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",

   "hidden_act": "silu",
   "hidden_size": 32,
   "initializer_range": 0.02,
+  "intermediate_size": 64,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f338a9a319bf14514b49acd6584aafcbf88b6577419b7131a5e288cd93a25f35
 size 16416904

 version https://git-lfs.github.com/spec/v1
+oid sha256:af442e1e12ad4b8ee057fd5c66cb19560b1e5bc4386161c2e75ea23212d51998
 size 16416904

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4db41f16b0975ad793347f0fe4fb7bbdd42920ded882e626fdb60e1df0cece
-size 22136

 version https://git-lfs.github.com/spec/v1
+oid sha256:e51505033c3c83339e0cf30cc16fe457db5e73bae25e73740ceff114858e9d73
+size 34424

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e4c374e5367233d34fcc135f4dd48f91e599a5deabccffcd8e9e702e9bb75d4
 size 16416896

 version https://git-lfs.github.com/spec/v1
+oid sha256:991f2681f36c72caee0191eb4a6a9ae847d275933907d402e0941c0c23aa79b8
 size 16416896

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 32854656
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",

 {
   "metadata": {
+    "total_size": 32866944
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",