Instructions to use dipta007/decomposeRL-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dipta007/decomposeRL-7b with Transformers:

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

pipe = pipeline("text-generation", model="dipta007/decomposeRL-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dipta007/decomposeRL-7b")
model = AutoModelForCausalLM.from_pretrained("dipta007/decomposeRL-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dipta007/decomposeRL-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dipta007/decomposeRL-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dipta007/decomposeRL-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dipta007/decomposeRL-7b

SGLang

How to use dipta007/decomposeRL-7b 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 "dipta007/decomposeRL-7b" \
    --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": "dipta007/decomposeRL-7b",
		"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 "dipta007/decomposeRL-7b" \
        --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": "dipta007/decomposeRL-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dipta007/decomposeRL-7b with Docker Model Runner:
```
docker model run hf.co/dipta007/decomposeRL-7b
```

Fix Highlights accuracy to match results table (macro 86.3, micro 84.4)

by dipta007 - opened 22 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-3

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -33,10 +33,10 @@ tags:
 ## Highlights
-- **84.5% micro-average balanced accuracy** across 9 in-domain claim-verification benchmarks (sample-weighted)
-- **84.6% macro-average balanced accuracy** across the same 9 benchmarks
 - Out-of-domain: **60.2% balanced accuracy on Coverbench**, **77.0% on LLM-AggreFact**
-- Strong on long-form evidence: 87% on Ex-FEVER, 92% on FEVEROUS, 76% on HoVer
 - Reasoning is **fully transparent**: the model emits its sub-claim checklist, every question it asked, every quote from evidence, and a final label
 ## Model Overview

 ## Highlights
+- **84.4% micro-average balanced accuracy** across 9 in-domain claim-verification benchmarks (sample-weighted)
+- **86.3% macro-average balanced accuracy** across the same 9 benchmarks
 - Out-of-domain: **60.2% balanced accuracy on Coverbench**, **77.0% on LLM-AggreFact**
+- Strong on long-form evidence: 88% on Ex-FEVER, 93% on FEVEROUS, 76% on HoVer
 - Reasoning is **fully transparent**: the model emits its sub-claim checklist, every question it asked, every quote from evidence, and a final label
 ## Model Overview