Instructions to use ThingAI/Quark-135m-Bilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThingAI/Quark-135m-Bilingual with Transformers:

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

pipe = pipeline("text-generation", model="ThingAI/Quark-135m-Bilingual", 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-135m-Bilingual", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ThingAI/Quark-135m-Bilingual with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThingAI/Quark-135m-Bilingual"
# 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-135m-Bilingual",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThingAI/Quark-135m-Bilingual

SGLang

How to use ThingAI/Quark-135m-Bilingual 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-135m-Bilingual" \
    --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-135m-Bilingual",
		"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-135m-Bilingual" \
        --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-135m-Bilingual",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThingAI/Quark-135m-Bilingual with Docker Model Runner:
```
docker model run hf.co/ThingAI/Quark-135m-Bilingual
```

ThingsAI commited on 2 days ago

Commit

2dfe12b

verified ·

1 Parent(s): f115d8d

Update config.json

Browse files

Files changed (1) hide show

config.json +11 -16

config.json CHANGED Viewed

@@ -1,8 +1,10 @@
 {
   "model_type": "quark",
-  "architectures": [
-    "QuarkForCausalLM"
-  ],
   "vocab_size": 65537,
   "d_model": 576,
   "n_heads": 9,
@@ -12,23 +14,16 @@
   "head_dim": 64,
   "max_seq_len": 2048,
   "rope_theta": 10000.0,
-  "rms_eps": 1e-05,
   "qkv_bias": true,
   "dropout": 0.0,
   "torch_dtype": "bfloat16",
   "sft_dataset": "MBZUAI/Bactrian-X (it+en)",
   "sft_steps": 4000,
-  "sft_loss": 1.8805,
-  "base_pretrain": "step_0030000 (15.7B tokens bilingual IT+EN)",
   "tokenizer": "ThingAI/QuarkTokenizer",
-  "languages": [
-    "it",
-    "en"
-  ],
-  "special_tokens": [
-    "<|user|>",
-    "<|assistant|>",
-    "<|end|>"
-  ],
-  "tie_word_embeddings": true
 }

 {
   "model_type": "quark",
+  "architectures": ["QuarkForCausalLM"],
+  "auto_map": {
+    "AutoConfig": "configuration_quark.QuarkConfig",
+    "AutoModelForCausalLM": "modeling_quark.QuarkForCausalLM"
+  },
   "vocab_size": 65537,
   "d_model": 576,
   "n_heads": 9,
   "head_dim": 64,
   "max_seq_len": 2048,
   "rope_theta": 10000.0,
+  "rms_eps": 1e-5,
   "qkv_bias": true,
   "dropout": 0.0,
   "torch_dtype": "bfloat16",
+  "tie_word_embeddings": true,
   "sft_dataset": "MBZUAI/Bactrian-X (it+en)",
   "sft_steps": 4000,
+  "sft_loss": 1.9,
+  "base_pretrain": "15.7B tokens bilingual IT+EN",
   "tokenizer": "ThingAI/QuarkTokenizer",
+  "languages": ["it", "en"],
+  "special_tokens": ["<|user|>", "<|assistant|>", "<|end|>"]
 }