Instructions to use tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70") model = AutoModelForCausalLM.from_pretrained("tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70", device_map="auto") 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 tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70
- SGLang
How to use tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70 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 "tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70" \ --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": "tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70", "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 "tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70" \ --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": "tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70 with Docker Model Runner:
docker model run hf.co/tomhu/Qwen3-Coder-Next-SWE-Prune-ACTIVATION-70
| { | |
| "auxiliary_files": [ | |
| ".gitattributes", | |
| "README.md", | |
| "chat_template.jinja", | |
| "generation_config.json", | |
| "merges.txt", | |
| "qwen3_coder_detector_sgl.py", | |
| "qwen3coder_tool_parser_vllm.py", | |
| "tokenizer.json", | |
| "tokenizer_config.json", | |
| "vocab.json" | |
| ], | |
| "completed_at_utc": "2026-08-13T17:53:37.147794+00:00", | |
| "elapsed_seconds": 272.11434280101093, | |
| "mapping_file": "expert_mapping.csv", | |
| "mapping_sha256": "2e0c5787de7325a46d76c37c59dfa69d4b14e40fae89533adfa7d27aa6b5ec0b", | |
| "num_experts_per_tok": 10, | |
| "num_layers": 48, | |
| "operation": "per-layer REAP top-score routed-expert pruning", | |
| "output_payload_bytes": 51166017024, | |
| "output_shards": [ | |
| { | |
| "file": "model-00001-of-00040.safetensors", | |
| "file_size": 1740017224, | |
| "payload_size": 1739956992, | |
| "sha256": "8386fa3111ba2294d46d83f02b32ba1ecadcc8b2f44d47df36a614b95966064a", | |
| "tensor_count": 491 | |
| }, | |
| { | |
| "file": "model-00002-of-00040.safetensors", | |
| "file_size": 1219484512, | |
| "payload_size": 1219416448, | |
| "sha256": "423ddde7d0405e73df6fd0383f720efd5940650f6499b1fd13a7dbd4956619e7", | |
| "tensor_count": 560 | |
| }, | |
| { | |
| "file": "model-00003-of-00040.safetensors", | |
| "file_size": 1311438216, | |
| "payload_size": 1311364096, | |
| "sha256": "753c290bf9705c67725e7c93caabd580cd45a745cafabfe353bdaf1db9f58541", | |
| "tensor_count": 609 | |
| }, | |
| { | |
| "file": "model-00004-of-00040.safetensors", | |
| "file_size": 1223679200, | |
| "payload_size": 1223610752, | |
| "sha256": "79bb45ed1fc175c0eda58a19d008f296f775b126dadc2b7a27f80ae92b8bc4b8", | |
| "tensor_count": 562 | |
| }, | |
| { | |
| "file": "model-00005-of-00040.safetensors", | |
| "file_size": 1246749224, | |
| "payload_size": 1246679424, | |
| "sha256": "f58559bb2fd8c8c98dac343c8065536ca54e13cac9f1650348a8c210c99ed47e", | |
| "tensor_count": 573 | |
| }, | |
| { | |
| "file": "model-00006-of-00040.safetensors", | |
| "file_size": 1322893192, | |
| "payload_size": 1322820992, | |
| "sha256": "8c495f36820e709db850560828aca0cf182eb1996cc29e84c10330080069cdda", | |
| "tensor_count": 593 | |
| }, | |
| { | |
| "file": "model-00007-of-00040.safetensors", | |
| "file_size": 1267721888, | |
| "payload_size": 1267650944, | |
| "sha256": "43f04b07150a4dba3f4b14cc4cbb70968e4f6c508d7e174bcb93d54b8c4ad086", | |
| "tensor_count": 583 | |
| }, | |
| { | |
| "file": "model-00008-of-00040.safetensors", | |
| "file_size": 1232068256, | |
| "payload_size": 1231999360, | |
| "sha256": "7d4ea44f0ac341f5b70a03e47c3b5c953356c4df61b707c7cbd02a6d9c95b685", | |
| "tensor_count": 566 | |
| }, | |
| { | |
| "file": "model-00009-of-00040.safetensors", | |
| "file_size": 1259333256, | |
| "payload_size": 1259262336, | |
| "sha256": "7b32428b7b8a64515c4a5bd84ceed2eb81ac8fd87df3c5340c6a832910cff60a", | |
| "tensor_count": 579 | |
| }, | |
| { | |
| "file": "model-00010-of-00040.safetensors", | |
| "file_size": 1240131552, | |
| "payload_size": 1240060928, | |
| "sha256": "6af129a7da2147585a02a9833f2882c20dd58bf0fce1aa0d60486aafe22abf66", | |
| "tensor_count": 575 | |
| }, | |
| { | |
| "file": "model-00011-of-00040.safetensors", | |
| "file_size": 1291761024, | |
| "payload_size": 1291690752, | |
| "sha256": "6e28d984e1662f779390e45dbd64c0aba32d9cd456764f00fa534e2dfdfce013", | |
| "tensor_count": 573 | |
| }, | |
| { | |
| "file": "model-00012-of-00040.safetensors", | |
| "file_size": 1257236096, | |
| "payload_size": 1257165184, | |
| "sha256": "b7ddbb57b44afbddd7e43af366d5c75503c590222100c0fc74eef9695081b98b", | |
| "tensor_count": 578 | |
| }, | |
| { | |
| "file": "model-00013-of-00040.safetensors", | |
| "file_size": 1261104256, | |
| "payload_size": 1261032448, | |
| "sha256": "824cab1ff3bd4f027df2a06702938f0cb85d168e840df9d37b6131c75e2d3be6", | |
| "tensor_count": 585 | |
| }, | |
| { | |
| "file": "model-00014-of-00040.safetensors", | |
| "file_size": 1246749800, | |
| "payload_size": 1246679424, | |
| "sha256": "9583cfe00b9bbe012c0aa1c1c7e411738a7719e59e5f0c662774f6985c66f213", | |
| "tensor_count": 573 | |
| }, | |
| { | |
| "file": "model-00015-of-00040.safetensors", | |
| "file_size": 1304344760, | |
| "payload_size": 1304273664, | |
| "sha256": "7576de1dda74244f0f4943902bf9d709ad1450378ec020cb4ce5939d4aee6941", | |
| "tensor_count": 579 | |
| }, | |
| { | |
| "file": "model-00016-of-00040.safetensors", | |
| "file_size": 1307244232, | |
| "payload_size": 1307169792, | |
| "sha256": "341c934e3f7e46017d5a7fbb9e506ce2646b833adf1005d4818e1541f37b9039", | |
| "tensor_count": 607 | |
| }, | |
| { | |
| "file": "model-00017-of-00040.safetensors", | |
| "file_size": 1236263360, | |
| "payload_size": 1236193664, | |
| "sha256": "56669e1f5f4c9f25ab9c3e4ba81cb2898a5b304c4a9502e8be3981ac99e69264", | |
| "tensor_count": 568 | |
| }, | |
| { | |
| "file": "model-00018-of-00040.safetensors", | |
| "file_size": 1217387936, | |
| "payload_size": 1217319296, | |
| "sha256": "ec163ef8b0177406a130a967ff86c554ea740dfad70d8abcfa72687ab24b6daf", | |
| "tensor_count": 559 | |
| }, | |
| { | |
| "file": "model-00019-of-00040.safetensors", | |
| "file_size": 1257236184, | |
| "payload_size": 1257165184, | |
| "sha256": "1f70e194070bac37e0382b3ff7025ce49f21cc617c77cd70f3707e9d5a4fcc59", | |
| "tensor_count": 578 | |
| }, | |
| { | |
| "file": "model-00020-of-00040.safetensors", | |
| "file_size": 1283045480, | |
| "payload_size": 1282975104, | |
| "sha256": "06e181c0a3cde53ad0c86f36d06c330729116e39aee91dedd0f3795fa293ec48", | |
| "tensor_count": 574 | |
| }, | |
| { | |
| "file": "model-00021-of-00040.safetensors", | |
| "file_size": 1253041544, | |
| "payload_size": 1252970880, | |
| "sha256": "8d0a66d7059f5b4ba4e764a9af6b022ac5795d7dd42d5aadea8a8065ded2174a", | |
| "tensor_count": 576 | |
| }, | |
| { | |
| "file": "model-00022-of-00040.safetensors", | |
| "file_size": 1253041576, | |
| "payload_size": 1252970880, | |
| "sha256": "51c788c9f218a72ae1b938abbe5485f5e59c0a99feca443247d534ba54a682ad", | |
| "tensor_count": 576 | |
| }, | |
| { | |
| "file": "model-00023-of-00040.safetensors", | |
| "file_size": 1256909728, | |
| "payload_size": 1256838144, | |
| "sha256": "f636e58548209a128f0fb57c54f0ca2c15bd1b121300752ed4648178f3528a69", | |
| "tensor_count": 583 | |
| }, | |
| { | |
| "file": "model-00024-of-00040.safetensors", | |
| "file_size": 1244652560, | |
| "payload_size": 1244582272, | |
| "sha256": "5e6ad267fa8c0c065e3a4920d542e75c27ecb276403707b78cb043755d7f93ed", | |
| "tensor_count": 572 | |
| }, | |
| { | |
| "file": "model-00025-of-00040.safetensors", | |
| "file_size": 1310636512, | |
| "payload_size": 1310565120, | |
| "sha256": "2539373b0440b7ba9f3592ec777c65c57fb93cd55fa686d90d0dc243ba5d4d54", | |
| "tensor_count": 582 | |
| }, | |
| { | |
| "file": "model-00026-of-00040.safetensors", | |
| "file_size": 1279979664, | |
| "payload_size": 1279906816, | |
| "sha256": "eb2f25b0ee411df42c05f24d35a9baa264bc78dff5d14c794e9f9a5921870877", | |
| "tensor_count": 594 | |
| }, | |
| { | |
| "file": "model-00027-of-00040.safetensors", | |
| "file_size": 1221582472, | |
| "payload_size": 1221513600, | |
| "sha256": "dea8e9c47bc07c4c4789acbad3d90deafd80736390513eaba04016d902b53e91", | |
| "tensor_count": 561 | |
| }, | |
| { | |
| "file": "model-00028-of-00040.safetensors", | |
| "file_size": 1261430736, | |
| "payload_size": 1261359488, | |
| "sha256": "411a8f22fd3f883ba5e5f61897f89f4e5d31f182ce009e695ed58df48877c7d8", | |
| "tensor_count": 580 | |
| }, | |
| { | |
| "file": "model-00029-of-00040.safetensors", | |
| "file_size": 1293531968, | |
| "payload_size": 1293460864, | |
| "sha256": "15bbf0b482cb1b4ef16f697f658b67d0a42148245214805d51dde9af66ade444", | |
| "tensor_count": 579 | |
| }, | |
| { | |
| "file": "model-00030-of-00040.safetensors", | |
| "file_size": 1253041496, | |
| "payload_size": 1252970880, | |
| "sha256": "c8bb0e79b40e6a1b1d01843998a74fd74fe093c0bd242783c15988714971e50d", | |
| "tensor_count": 576 | |
| }, | |
| { | |
| "file": "model-00031-of-00040.safetensors", | |
| "file_size": 1269819760, | |
| "payload_size": 1269748096, | |
| "sha256": "f87ddd92fe3282e9052a8037455cfdc58791c14f45b64a1f3663f231572d9acc", | |
| "tensor_count": 584 | |
| }, | |
| { | |
| "file": "model-00032-of-00040.safetensors", | |
| "file_size": 1244652536, | |
| "payload_size": 1244582272, | |
| "sha256": "8e12f19627c2466fa8fad4d8b155e93ef534d48d34792740d70c27c198b393d9", | |
| "tensor_count": 572 | |
| }, | |
| { | |
| "file": "model-00033-of-00040.safetensors", | |
| "file_size": 1248520616, | |
| "payload_size": 1248449536, | |
| "sha256": "5bc79f826dd1fb3c799ec2677d62e23fcf5c68bca6c39889865c26f566d79d0a", | |
| "tensor_count": 579 | |
| }, | |
| { | |
| "file": "model-00034-of-00040.safetensors", | |
| "file_size": 1277080120, | |
| "payload_size": 1277010688, | |
| "sha256": "f9a343c991f2d753b0902ef5bb347985688b0a651957e78470733825e075d76f", | |
| "tensor_count": 566 | |
| }, | |
| { | |
| "file": "model-00035-of-00040.safetensors", | |
| "file_size": 1286597960, | |
| "payload_size": 1286525312, | |
| "sha256": "d57be07a287f21868e4c5ea68d5fec34a26507c9705cb2d395fb6af717f9d9fe", | |
| "tensor_count": 592 | |
| }, | |
| { | |
| "file": "model-00036-of-00040.safetensors", | |
| "file_size": 1277882448, | |
| "payload_size": 1277809664, | |
| "sha256": "8ab40501fc6af3b7a818e252e2917cf51493db983afffef17e97b8f00b329ed0", | |
| "tensor_count": 593 | |
| }, | |
| { | |
| "file": "model-00037-of-00040.safetensors", | |
| "file_size": 1211096088, | |
| "payload_size": 1211027840, | |
| "sha256": "8dadd16953f7431a6ce23028c98ac52736e4f1a37dade421bb2826846eba2dcb", | |
| "tensor_count": 556 | |
| }, | |
| { | |
| "file": "model-00038-of-00040.safetensors", | |
| "file_size": 1253041672, | |
| "payload_size": 1252970880, | |
| "sha256": "78410eff5186e0ecce5fdb86a01ffc358c43375f387c74234f18ec9a0e47302f", | |
| "tensor_count": 576 | |
| }, | |
| { | |
| "file": "model-00039-of-00040.safetensors", | |
| "file_size": 1293531888, | |
| "payload_size": 1293460864, | |
| "sha256": "e0dd465a3bc1523805ee13e53cc6d50d43ab2d3fde30b08b6f9a1c3df233bcf9", | |
| "tensor_count": 579 | |
| }, | |
| { | |
| "file": "model-00040-of-00040.safetensors", | |
| "file_size": 1452855416, | |
| "payload_size": 1452806144, | |
| "sha256": "0bfbe0d3a2d1be59a29615d68bfe68613767ef88432be362553853bc3edb91e7", | |
| "tensor_count": 398 | |
| } | |
| ], | |
| "output_tensor_count": 22839, | |
| "renumbering": "retained source expert ids sorted ascending and mapped to contiguous ids", | |
| "retained_experts_per_layer": 154, | |
| "schema_version": 1, | |
| "score_column": "mean_output_l2_selected_route", | |
| "score_csv": "/data/haichuan/qwen3_coder_next_vllm_reap/runs/qwen_rebench500_bf16_fixed_formal_20260811T181201Z/reap/rebench_decode_reap_scores.csv", | |
| "score_csv_sha256": "ba234ff7ef4b624bc85e1b12dc49b1b1f25fcb88d6e4ea99ff3eedb048efea48", | |
| "score_primary_phase": "decode", | |
| "score_source_provenance": { | |
| "cross_precision": false, | |
| "decode_tokens": 3277544, | |
| "model_config_sha256": "a7b8098d3b05777f12bb5677a26bf1240a1bb09def1b06b29e6be86cae2e84f8", | |
| "model_index_sha256": "e54c170589a729006db825100b4c69cf1c485ee89d3e8dd30aec9dccbf9cea1b", | |
| "present": true, | |
| "run_config": "/data/haichuan/qwen3_coder_next_vllm_reap/runs/qwen_rebench500_bf16_fixed_formal_20260811T181201Z/RUN_CONFIG.txt", | |
| "run_config_sha256": "241a02425215e191b5ed1229608eb69ff9fb09bb97557d4bd6c199243dc361d4", | |
| "score_checkpoint_precision": "bf16", | |
| "score_manifest": "/data/haichuan/qwen3_coder_next_vllm_reap/runs/qwen_rebench500_bf16_fixed_formal_20260811T181201Z/reap/rebench_decode_reap_scores.manifest.json", | |
| "score_manifest_sha256": "b3cd14631673939df1abb3f8c88d2a6f657e5c8ab70688aee3422a7ab544cc96", | |
| "server_epoch": "qwen_rebench500_bf16_fixed_formal_20260811T181201Z", | |
| "target_checkpoint_precision": "bf16", | |
| "verified": true | |
| }, | |
| "selection": "largest score; ties broken by smaller source expert id", | |
| "source_config_sha256": "a7b8098d3b05777f12bb5677a26bf1240a1bb09def1b06b29e6be86cae2e84f8", | |
| "source_experts_per_layer": 512, | |
| "source_index_sha256": "e54c170589a729006db825100b4c69cf1c485ee89d3e8dd30aec9dccbf9cea1b", | |
| "source_model": "/source", | |
| "source_payload_bytes": 159348782592, | |
| "tool": "prune_qwen3_next_reap_bf16.py", | |
| "tool_version": "1.0-bf16", | |
| "validation": { | |
| "config_num_experts": true, | |
| "contiguous_expert_ids_per_layer": true, | |
| "every_output_header_matches_source_mapping_plan": true, | |
| "index_matches_all_shard_headers": true, | |
| "router_rows_match_mapping": true, | |
| "score_checkpoint_fingerprint_matches": true, | |
| "source_size_and_mtime_unchanged": true, | |
| "three_bf16_weight_tensors_per_expert": true | |
| }, | |
| "warnings": [] | |
| } | |