Instructions to use firstgradeai/tinylama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use firstgradeai/tinylama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="firstgradeai/tinylama")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("firstgradeai/tinylama") model = AutoModelForCausalLM.from_pretrained("firstgradeai/tinylama") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use firstgradeai/tinylama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "firstgradeai/tinylama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "firstgradeai/tinylama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/firstgradeai/tinylama
- SGLang
How to use firstgradeai/tinylama 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 "firstgradeai/tinylama" \ --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": "firstgradeai/tinylama", "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 "firstgradeai/tinylama" \ --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": "firstgradeai/tinylama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use firstgradeai/tinylama with Docker Model Runner:
docker model run hf.co/firstgradeai/tinylama
Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +1 -6
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
-
"pad_token": "<
|
| 21 |
"unk_token": {
|
| 22 |
"content": "<unk>",
|
| 23 |
"lstrip": false,
|
|
|
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
+
"pad_token": "</s>",
|
| 21 |
"unk_token": {
|
| 22 |
"content": "<unk>",
|
| 23 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -60,7 +60,7 @@
|
|
| 60 |
"eos_token": "</s>",
|
| 61 |
"legacy": false,
|
| 62 |
"model_max_length": 1000000000000000019884624838656,
|
| 63 |
-
"pad_token": "<
|
| 64 |
"padding_side": "right",
|
| 65 |
"sp_model_kwargs": {},
|
| 66 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 60 |
"eos_token": "</s>",
|
| 61 |
"legacy": false,
|
| 62 |
"model_max_length": 1000000000000000019884624838656,
|
| 63 |
+
"pad_token": "</s>",
|
| 64 |
"padding_side": "right",
|
| 65 |
"sp_model_kwargs": {},
|
| 66 |
"tokenizer_class": "LlamaTokenizer",
|