Instructions to use TinyPixel/small-llama2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TinyPixel/small-llama2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TinyPixel/small-llama2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TinyPixel/small-llama2") model = AutoModelForCausalLM.from_pretrained("TinyPixel/small-llama2") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TinyPixel/small-llama2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TinyPixel/small-llama2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TinyPixel/small-llama2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TinyPixel/small-llama2
- SGLang
How to use TinyPixel/small-llama2 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/small-llama2" \ --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/small-llama2", "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/small-llama2" \ --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/small-llama2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TinyPixel/small-llama2 with Docker Model Runner:
docker model run hf.co/TinyPixel/small-llama2
Upload LlamaForCausalLM
Browse files- config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 1024,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size":
|
| 13 |
"max_position_embeddings": 1024,
|
| 14 |
"model_type": "llama",
|
| 15 |
"num_attention_heads": 8,
|
|
|
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 1024,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 1376,
|
| 13 |
"max_position_embeddings": 1024,
|
| 14 |
"model_type": "llama",
|
| 15 |
"num_attention_heads": 8,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc4f97faedeaab0dc5e72d4443dc3a94f8392822068c9547c696aaecc2deb0fd
|
| 3 |
+
size 333248704
|