Instructions to use HenrySentinel/tinyMind with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HenrySentinel/tinyMind with Transformers:

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

pipe = pipeline("text-generation", model="HenrySentinel/tinyMind", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HenrySentinel/tinyMind", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HenrySentinel/tinyMind with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HenrySentinel/tinyMind

SGLang

How to use HenrySentinel/tinyMind 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 "HenrySentinel/tinyMind" \
    --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": "HenrySentinel/tinyMind",
		"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 "HenrySentinel/tinyMind" \
        --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": "HenrySentinel/tinyMind",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HenrySentinel/tinyMind with Docker Model Runner:
```
docker model run hf.co/HenrySentinel/tinyMind
```

HenrySentinel commited on 14 days ago

Commit

22c34d9

verified ·

1 Parent(s): 6f5cb36

Update tokenizer with chat template and pad token

Browse files

Files changed (1) hide show

tokenizer_config.json +2 -12

tokenizer_config.json CHANGED Viewed

@@ -1,20 +1,10 @@
 {
   "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
-  "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"

 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% elif message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "model_max_length": 512,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"