Instructions to use jasonlingg/rlm-explorer-qwen3-8b-qasper-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jasonlingg/rlm-explorer-qwen3-8b-qasper-sft with PEFT:
Task type is invalid.
- Transformers
How to use jasonlingg/rlm-explorer-qwen3-8b-qasper-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jasonlingg/rlm-explorer-qwen3-8b-qasper-sft")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jasonlingg/rlm-explorer-qwen3-8b-qasper-sft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jasonlingg/rlm-explorer-qwen3-8b-qasper-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jasonlingg/rlm-explorer-qwen3-8b-qasper-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jasonlingg/rlm-explorer-qwen3-8b-qasper-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jasonlingg/rlm-explorer-qwen3-8b-qasper-sft
- SGLang
How to use jasonlingg/rlm-explorer-qwen3-8b-qasper-sft 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 "jasonlingg/rlm-explorer-qwen3-8b-qasper-sft" \ --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": "jasonlingg/rlm-explorer-qwen3-8b-qasper-sft", "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 "jasonlingg/rlm-explorer-qwen3-8b-qasper-sft" \ --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": "jasonlingg/rlm-explorer-qwen3-8b-qasper-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jasonlingg/rlm-explorer-qwen3-8b-qasper-sft with Docker Model Runner:
docker model run hf.co/jasonlingg/rlm-explorer-qwen3-8b-qasper-sft
Download evaluation/final.manifest.json from jasonlingg/rlm-explorer-qwen3-8b-qasper-sft: direct link, hf CLI and curl.
- Browser
- Download file 3.65 kB
-
https://huggingface.co/jasonlingg/rlm-explorer-qwen3-8b-qasper-sft/resolve/main/evaluation/final.manifest.json
- Command line
-
hf download hf://jasonlingg/rlm-explorer-qwen3-8b-qasper-sft/evaluation/final.manifest.json
-
curl -L -o final.manifest.json https://huggingface.co/jasonlingg/rlm-explorer-qwen3-8b-qasper-sft/resolve/main/evaluation/final.manifest.json
3.65 kB
| { | |
| "question_ids": [ | |
| "qasper_test_010fd15696580d9924ac0275a4ff269005e5808d", | |
| "qasper_test_0ac6fbd81e2dd95b800283dc7e59ce969d45fc02", | |
| "qasper_test_0ba1514fb193c52a15c31ffdcd5c3ddbb2bb2c40", | |
| "qasper_test_0d3193d17c0a4edc8fa9854f279c2a1b878e8b29", | |
| "qasper_test_1edfe390828f02a2db9a88454421c7f3d4cdd611", | |
| "qasper_test_22488c8628b6db5fd708b6471c31a8eac31f66df", | |
| "qasper_test_3e3d123960e40bcb1618e11999bd2031ccc1d155", | |
| "qasper_test_3f717e6eceab0a066af65ddf782c1ebc502c28c0", | |
| "qasper_test_4e0df856b39055a9ba801cc9c8e56d5b069bda11", | |
| "qasper_test_5138121b9e9bd56962e69bfe49d5df5301cb7745", | |
| "qasper_test_592df9831692b8fde213257ed1894344da3e0594", | |
| "qasper_test_5fd112980d0dd7f7ce30e6273fe6e7b230b13225", | |
| "qasper_test_610fc593638c5e9809ea9839912d0b282541d42d", | |
| "qasper_test_63279ecb2ba4e51c1225e63b81cb021abc10d0d1", | |
| "qasper_test_63eda2af88c35a507fbbfda0ec1082f58091883a", | |
| "qasper_test_71e1f06daf6310609d00850340e64a846fbe2dfb", | |
| "qasper_test_732bd97ae34541f215c436e2a1b98db1649cba27", | |
| "qasper_test_803babb71e1bdaf507847d6c712585f4128e9f47", | |
| "qasper_test_84f9952814d6995bc99bbb3abb372d90ef2f28b4", | |
| "qasper_test_86c867b393db0ec4ad09abb48cc1353cac47ea4c", | |
| "qasper_test_946d7c877d363f549f84e9500c852dce70ae5d36", | |
| "qasper_test_9f1e60ee86a5c46abe75b67ef369bf92a5090568", | |
| "qasper_test_a17fc7b96753f85aee1d2036e2627570f4b50c30", | |
| "qasper_test_a7e1b13cc42bfe78d37b9c943de6288e5f00f01b", | |
| "qasper_test_a86758696926f2db71f982dc1a4fa4404988544e", | |
| "qasper_test_a926d71e6e58066d279d9f7dc3210cd43f410164", | |
| "qasper_test_aa287673534fc05d8126c8e3486ca28821827034", | |
| "qasper_test_aa7c5386aedfb13a361a2629b67cb54277e208d2", | |
| "qasper_test_be0b438952048fe6bb91c61ba48e529d784bdcea", | |
| "qasper_test_c21675d8a90bda624d27e5535d1c10f08fcbc16b", | |
| "qasper_test_c626637ed14dee3049b87171ddf326115e59d9ee", | |
| "qasper_test_d5d4504f419862275a532b8e53d0ece16e0ae8d1", | |
| "qasper_test_d976c22e9d068e4e31fb46e929023459f8290a63", | |
| "qasper_test_e0b8a2649e384bbdb17472f8da2c3df4134b1e57", | |
| "qasper_test_e3c44964eb6ddc554901244eb6595f26a9bae47e", | |
| "qasper_test_e500948fa01c74e5cb3e6774f66aaa9ad4b3e435", | |
| "qasper_test_f1e70b63c45ab0fc35dc63de089c802543e30c8f", | |
| "qasper_test_f3b851c9063192c86a3cc33b2328c02efa41b668", | |
| "qasper_test_fa468c31dd0f9095d7cec010f2262eeed565a7d2", | |
| "qasper_test_faffcc6ef27c1441e6528f924e320368430d8da3" | |
| ], | |
| "questions_sha256": "5720a5220ff9e47eb2465028d9592551d4575830ec476dfafc31a4470a11d4d0", | |
| "corpus_sha256": "ee9e3b2986845194cf9a25dbd1ea1ab2cb8e44cd5e385e5cefcb8f7665335a9f", | |
| "max_steps": 10, | |
| "seed": 42, | |
| "reward_version": "outcome-v1", | |
| "workers": 1, | |
| "require_evidence": true, | |
| "vector_index": false, | |
| "decoding": [ | |
| "{\"max_tokens\": 1024, \"temperature\": 0.0}" | |
| ], | |
| "comparison_id": "92b285cd941627c6edb8067fcb7995c446067d6f5380b640b48535838015218e", | |
| "split": "/workspace/eval-data/qasper-test-abstention-v1/benchmark.json", | |
| "checkpoint_id": "/workspace/sft_qwen3_qasper_v2/final", | |
| "base_model": "Qwen/Qwen3-8B", | |
| "git_commit": "d7e6efa2b9f90af32584f6973eff364389cbf8ae", | |
| "git_status": [], | |
| "python": "3.12.3", | |
| "platform": "Linux-6.8.0-124-generic-x86_64-with-glibc2.39", | |
| "torch": "2.8.0+cu128", | |
| "gpu": "NVIDIA L4", | |
| "policy_settings": { | |
| "qwen_sft_policy": { | |
| "max_tokens": 1024, | |
| "temperature": 0.0, | |
| "base_revision": "b968826d9c46dd6066d109eabc6255188de91218" | |
| } | |
| }, | |
| "run_id": "20260917_175910_7935cb72add2", | |
| "run_label": "qwen3_sft_final_abstention_v1", | |
| "reward_weights": { | |
| "answer": 0.8, | |
| "citation_precision": 0.1, | |
| "citation_recall": 0.1 | |
| } | |
| } |