Instructions to use TinyPixel/tinyllama-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TinyPixel/tinyllama-random with Transformers:

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

pipe = pipeline("text-generation", model="TinyPixel/tinyllama-random")

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

tokenizer = AutoTokenizer.from_pretrained("TinyPixel/tinyllama-random")
model = AutoModelForCausalLM.from_pretrained("TinyPixel/tinyllama-random", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TinyPixel/tinyllama-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TinyPixel/tinyllama-random

SGLang

How to use TinyPixel/tinyllama-random 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 "TinyPixel/tinyllama-random" \
    --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": "TinyPixel/tinyllama-random",
		"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 "TinyPixel/tinyllama-random" \
        --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": "TinyPixel/tinyllama-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TinyPixel/tinyllama-random with Docker Model Runner:
```
docker model run hf.co/TinyPixel/tinyllama-random
```

TinyPixel commited on Nov 22, 2023

Commit

52e8ef3

1 Parent(s): b29c260

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -11,12 +11,12 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
-  "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

 {
+  "_name_or_path": "TinyPixel/gpt_2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
+  "n_ctx": 2048,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
+  "n_positions": 2048,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8269ad719ae074e93343e3c1a959c0136fa6e2863af402252700eb002c1155
-size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f5c8700812e5665e15b778ad9ef346535f67ea2c2de68fb48f7553092bcfac5
+size 500919936