Instructions to use Isotonic/DR1-1.5b-JSON_extraction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Isotonic/DR1-1.5b-JSON_extraction with Transformers:

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

pipe = pipeline("text-generation", model="Isotonic/DR1-1.5b-JSON_extraction")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Isotonic/DR1-1.5b-JSON_extraction")
model = AutoModelForCausalLM.from_pretrained("Isotonic/DR1-1.5b-JSON_extraction")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Isotonic/DR1-1.5b-JSON_extraction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Isotonic/DR1-1.5b-JSON_extraction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Isotonic/DR1-1.5b-JSON_extraction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Isotonic/DR1-1.5b-JSON_extraction

SGLang

How to use Isotonic/DR1-1.5b-JSON_extraction 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 "Isotonic/DR1-1.5b-JSON_extraction" \
    --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": "Isotonic/DR1-1.5b-JSON_extraction",
		"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 "Isotonic/DR1-1.5b-JSON_extraction" \
        --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": "Isotonic/DR1-1.5b-JSON_extraction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Isotonic/DR1-1.5b-JSON_extraction with Docker Model Runner:
```
docker model run hf.co/Isotonic/DR1-1.5b-JSON_extraction
```

Isotonic commited on Apr 12, 2025

Commit

25d1da8

verified ·

1 Parent(s): 8be9bd7

Update config.json

Browse files

Files changed (1) hide show

config.json +4 -2

config.json CHANGED Viewed

@@ -1,4 +1,5 @@
 {
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -9,7 +10,7 @@
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
@@ -25,6 +26,7 @@
   "transformers_version": "4.51.2",
   "unsloth_version": "2025.2.4",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
-}

 {
+  "_name_or_path": "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "transformers_version": "4.51.2",
   "unsloth_version": "2025.2.4",
   "use_cache": false,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
+}