Text Generation
Transformers
Safetensors
Italian
English
quark
causal-lm
bilingual
italian
english
small-language-model
trained-from-scratch
instruct
sft
chat
conversational
custom_code
Instructions to use ThingAI/Quark-270m-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ThingAI/Quark-270m-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ThingAI/Quark-270m-Instruct", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ThingAI/Quark-270m-Instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ThingAI/Quark-270m-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ThingAI/Quark-270m-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ThingAI/Quark-270m-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ThingAI/Quark-270m-Instruct
- SGLang
How to use ThingAI/Quark-270m-Instruct 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 "ThingAI/Quark-270m-Instruct" \ --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": "ThingAI/Quark-270m-Instruct", "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 "ThingAI/Quark-270m-Instruct" \ --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": "ThingAI/Quark-270m-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ThingAI/Quark-270m-Instruct with Docker Model Runner:
docker model run hf.co/ThingAI/Quark-270m-Instruct
Upload configuration_quark.py with huggingface_hub
Browse files- configuration_quark.py +12 -0
configuration_quark.py
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
class QuarkConfig(PretrainedConfig):
|
| 4 |
+
model_type = "quark"
|
| 5 |
+
def __init__(self, vocab_size=65537, d_model=768, n_heads=12, n_kv_heads=4,
|
| 6 |
+
n_layers=32, d_ff=2048, head_dim=64, max_seq_len=2048,
|
| 7 |
+
rope_theta=10000.0, rms_eps=1e-5, qkv_bias=True, dropout=0.0, **kwargs):
|
| 8 |
+
self.vocab_size=vocab_size; self.d_model=d_model; self.n_heads=n_heads
|
| 9 |
+
self.n_kv_heads=n_kv_heads; self.n_layers=n_layers; self.d_ff=d_ff
|
| 10 |
+
self.head_dim=head_dim; self.max_seq_len=max_seq_len; self.rope_theta=rope_theta
|
| 11 |
+
self.rms_eps=rms_eps; self.qkv_bias=qkv_bias; self.dropout=dropout
|
| 12 |
+
super().__init__(**kwargs)
|