Instructions to use ArchSpace-Collection/OLMo3-1B-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArchSpace-Collection/OLMo3-1B-stage2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ArchSpace-Collection/OLMo3-1B-stage2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ArchSpace-Collection/OLMo3-1B-stage2") model = AutoModelForCausalLM.from_pretrained("ArchSpace-Collection/OLMo3-1B-stage2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ArchSpace-Collection/OLMo3-1B-stage2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ArchSpace-Collection/OLMo3-1B-stage2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ArchSpace-Collection/OLMo3-1B-stage2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ArchSpace-Collection/OLMo3-1B-stage2
- SGLang
How to use ArchSpace-Collection/OLMo3-1B-stage2 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 "ArchSpace-Collection/OLMo3-1B-stage2" \ --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": "ArchSpace-Collection/OLMo3-1B-stage2", "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 "ArchSpace-Collection/OLMo3-1B-stage2" \ --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": "ArchSpace-Collection/OLMo3-1B-stage2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ArchSpace-Collection/OLMo3-1B-stage2 with Docker Model Runner:
docker model run hf.co/ArchSpace-Collection/OLMo3-1B-stage2
| { | |
| "schema": "olmo3.base.hf_export/v1", | |
| "source": { | |
| "checkpoint_metadata_sha256": "a0e2ceea009f7ccbef07e252c14db38d6210a7ae1c6c17210d24738d36680dcc", | |
| "iteration": 47684, | |
| "model_schema_sha256": "5be7d972eb3294c31abe5a6ea18bb1b2c34e2ca8225a32a9bf1673fe5d67e4fd", | |
| "parameter_count_with_padded_vocab": 1484916736, | |
| "run_id": "o3b1b-s2-s8192-g256-m1-tp1-cp2-dp256-hsdp32-b8-halo-norecomp-lr2p071235e4-save10000-512npu-share-20260801-v1" | |
| }, | |
| "stage": "stage2", | |
| "target": { | |
| "format": "huggingface_olmo3_safetensors", | |
| "padded_vocab_size": 100352, | |
| "parameter_count": 1484613632, | |
| "tensor_count": 179, | |
| "tensor_sha256": { | |
| "lm_head.weight": "f2dd12372bd63c4275de4fbfcd1f0a32213a584f252d9a5f8df8a698146f3c73", | |
| "model.embed_tokens.weight": "c9a6a623dc0286882bebd3cbabe97916b9fced48ca485aec1c0eefb7b9c533de", | |
| "model.layers.0.mlp.down_proj.weight": "d1cc834dd9b670f6c25b42e280eae84636a588b84e618c3d320e4099eb798762", | |
| "model.layers.0.mlp.gate_proj.weight": "8da09f8c7117eb54f60fd3175cfc53526c94ca9f7e8fc80d431e1ea18356ecb1", | |
| "model.layers.0.mlp.up_proj.weight": "b13a99399f161ddfee642b965d873f3706fbae0c9b344531647756e407a7a1bc", | |
| "model.layers.0.post_attention_layernorm.weight": "cc5ef013aa5b09e4fb4dd51a8fe52256826c35b81e438541b97de89862c7b6d4", | |
| "model.layers.0.post_feedforward_layernorm.weight": "041e41b7be38e6b2dc2c88bef9beffd085cfb27189798c6d395153f183eb08c1", | |
| "model.layers.0.self_attn.k_norm.weight": "2062143ec3b00d0b7f56765b5548432f1620b0cc34fb75e67d35d959fdb5e02e", | |
| "model.layers.0.self_attn.k_proj.weight": "8a43bea58e1ba8f3edaa7b8d2a7abb75b89950280e8138fff4409ed6fa07efe6", | |
| "model.layers.0.self_attn.o_proj.weight": "65e03e25c22334826a1903af920cddb26acd5611b60a91a16fdb5e41c6578d59", | |
| "model.layers.0.self_attn.q_norm.weight": "f30e920834f741156762a893ba2bddfcc6c244216de85ed8375d63f27f5cf123", | |
| "model.layers.0.self_attn.q_proj.weight": "4910f5978d4ae3f199a97f7971627d791790d0475c2ba8793ffec8390740047e", | |
| "model.layers.0.self_attn.v_proj.weight": "f3783c615561fd8fb8bd9c8e7ecacb47c41bc301a395e19b82029760daf47d17", | |
| "model.layers.1.mlp.down_proj.weight": "5d3a757c9fb746498d83db49692ab9cef180da162e0c5f4e264f7a1339fc9976", | |
| "model.layers.1.mlp.gate_proj.weight": "691929c87a0cec3053004b81cc740da8cf46d8a37d70de6bda1799cc3ab1b9ac", | |
| "model.layers.1.mlp.up_proj.weight": "b592645c0617c60f9377642f507acbe877bb1e52ed3c9b533377f4cf170fadb5", | |
| "model.layers.1.post_attention_layernorm.weight": "3c7d19e8d59cca97d62b6925e06a7d0a098bef86d9e3e36524846520eab095d2", | |
| "model.layers.1.post_feedforward_layernorm.weight": "869e7f9a406b80eedf5a8c2e064e26f78e69562679ccde8b037609dfd975bd1c", | |
| "model.layers.1.self_attn.k_norm.weight": "32ecb8593d4e37e61edaa02dd73bef5d8828dd8a64e8189e8e0141c386c0df86", | |
| "model.layers.1.self_attn.k_proj.weight": "a386e4d536004e0938768a7986333e27c1e7a547985563164429afd7505d1178", | |
| "model.layers.1.self_attn.o_proj.weight": "fa301efcd54ded33689ff58ee3429fbef43d708d79f670b942def67a9f315d0e", | |
| "model.layers.1.self_attn.q_norm.weight": "6359858bd1ae003bc3df390199ba5f5c7e34d80a04e09cb5b0e89fea7f5e5eed", | |
| "model.layers.1.self_attn.q_proj.weight": "ee9160d5d29e261b7a280e136a50520461f56d4275e0133de9f7e4e3cdd7a068", | |
| "model.layers.1.self_attn.v_proj.weight": "e8f85a9c1c1b6454198dd26ca6c3b1fdb9626f10a62d610554936f9070d76b45", | |
| "model.layers.10.mlp.down_proj.weight": "1298387c586bca0066bff20805f0820caab379abe1a2c165d0f9d9a50508447c", | |
| "model.layers.10.mlp.gate_proj.weight": "9a9109f32ffe9f4c3eaca0ce0374fec0be1867e60feb1d610a5ad9178ad86b85", | |
| "model.layers.10.mlp.up_proj.weight": "c8627c0e6b65a1fd635bc3e796b21819e2ebd8d362c430822777a176feee6633", | |
| "model.layers.10.post_attention_layernorm.weight": "eb63ca9f2899680395b39069dd84a24bc2ecb53486c33cca48ccd73052fde706", | |
| "model.layers.10.post_feedforward_layernorm.weight": "b2b33f02b6a8b020be07177971b2320202056e2905f82d84e7445ad601e1021c", | |
| "model.layers.10.self_attn.k_norm.weight": "eefcebead2b48683d5825b3bc481bd62199f4657e330dd1153be022989fe1766", | |
| "model.layers.10.self_attn.k_proj.weight": "0d3aa5a9bb719e6b4cc3e8018d4675f38d78b273314970dcfdcc4b8afba56b19", | |
| "model.layers.10.self_attn.o_proj.weight": "f2bf027e0a2e57a0cae5e7d008d91324026b3fb70bc4417c90a73c4ddbefb4a9", | |
| "model.layers.10.self_attn.q_norm.weight": "eadfd8e76f9373cfba3769d1514716c84a363f203844350a03299e8f61daac98", | |
| "model.layers.10.self_attn.q_proj.weight": "3b756fc1ca2eaf3d633e0ca8266470db380922955ce7a29984c0b023158012ce", | |
| "model.layers.10.self_attn.v_proj.weight": "fdf72dd86e8d53caa827e17cc85a44264a9fa8b376d6cfb949d04eb34f5d51c9", | |
| "model.layers.11.mlp.down_proj.weight": "3034aac625dc191642c98832e93c8dd8dfc1e2791b69c5c698ed344f70b38dce", | |
| "model.layers.11.mlp.gate_proj.weight": "ce0bfb049b561a1437749291067d61836ef1711b861b7e1e332fcded2d25b449", | |
| "model.layers.11.mlp.up_proj.weight": "9c6d54660a25f205e414e3fc0f3212af60ff4970db84d5e08cc0353af0a0e40d", | |
| "model.layers.11.post_attention_layernorm.weight": "8cc3c3809c799896aa28f63d46b57877d3548f2bf64cf6f3b7cfa5cde64c8537", | |
| "model.layers.11.post_feedforward_layernorm.weight": "84a896d9640d793b3c900f8314509ea092799e34baf17a19440d7c3b8e4cf750", | |
| "model.layers.11.self_attn.k_norm.weight": "2f37457f5bbba3ba4e218b3858d4ef61b9ffae3d09ef7c41cb46442b44b1b5ca", | |
| "model.layers.11.self_attn.k_proj.weight": "75528ca2ac586e368e7df4f517b8a14297ce1689827c91569bdadfc45931eb15", | |
| "model.layers.11.self_attn.o_proj.weight": "35907f04dd43f11ff3ec961a067112f483bed98ef305479fad84a3892376db66", | |
| "model.layers.11.self_attn.q_norm.weight": "c0b6b51a400dbe552c323e128d5690b5bb13d5be40e159bf59694266b037c030", | |
| "model.layers.11.self_attn.q_proj.weight": "4368336942659b6f5397ddbe63d3f201dae45a8fd30eaebb8167cbeab7bd210e", | |
| "model.layers.11.self_attn.v_proj.weight": "1ac18dd3cebf87a7f580761252631f8e1195f4ccc667a1c9397e98cb4c8e818d", | |
| "model.layers.12.mlp.down_proj.weight": "5ecd5d77789360d5b19c3f75bc5cb55400a00d5bdf79554d4fe5f58c07f37b91", | |
| "model.layers.12.mlp.gate_proj.weight": "183a215cc34a7b72d54b9f89b1173fc8f66de9a94373df11df0d0b821093de40", | |
| "model.layers.12.mlp.up_proj.weight": "fde5bfbc0bbf8d40063c49b64cde3a3cdf40236196cd295945bd8731ed93f1d3", | |
| "model.layers.12.post_attention_layernorm.weight": "adc6a53030bccb17f1c001a75fd0e05c164189dae6a200e1b405e27bcf3272a0", | |
| "model.layers.12.post_feedforward_layernorm.weight": "ce8e56984a787d1e3b3e8043e0cd835f4431add190f64b1a7b1922598ab5e80e", | |
| "model.layers.12.self_attn.k_norm.weight": "ac6b5c88f63120a08fda43502b17801b99aa71833d45fae3bfc579dd07449d3d", | |
| "model.layers.12.self_attn.k_proj.weight": "8005e159e39274ab530bbca7d50516764e20cd479d3c542439b208c7a02c6b23", | |
| "model.layers.12.self_attn.o_proj.weight": "9076b001e5a35b64c2864c098e0a326bb7983e39a49a8a022e8cf3cf509ae4d2", | |
| "model.layers.12.self_attn.q_norm.weight": "09816e235768b977510119d4b69422882f3670ee6d007af9df8a9a41b3cec1bb", | |
| "model.layers.12.self_attn.q_proj.weight": "834e157914d99bcc1c5ff7738ea49615a78fe4c1d421fafd7d030722c8480642", | |
| "model.layers.12.self_attn.v_proj.weight": "1063f76bb027222884ef709c7c130dd2431deba7b50a64439e3256ea7ed3f51e", | |
| "model.layers.13.mlp.down_proj.weight": "c71761c5b137e2f3ff699cf78542468a33ec28347b62022753775c0c16ff6fa7", | |
| "model.layers.13.mlp.gate_proj.weight": "a5d46e0987044ad7d785a6252334c4954b6ba502d596dc5293e2411f518422a1", | |
| "model.layers.13.mlp.up_proj.weight": "c1ddb86084ca8406a02c27800e2288df637cdd5b68d01035b64fe4d1f9ae6296", | |
| "model.layers.13.post_attention_layernorm.weight": "7cab95f7b48245bd93d527128109ff404d5052538a045d33ee3a367675ffb688", | |
| "model.layers.13.post_feedforward_layernorm.weight": "4a293a12fc18595df6364a4361bbeba191b9b6cf48bcc8c157c45308b749edf0", | |
| "model.layers.13.self_attn.k_norm.weight": "c4636096f435c66288a0f8c4ec68f2b096a149524e2e4aae5c6268613876ba19", | |
| "model.layers.13.self_attn.k_proj.weight": "4b0e227adc328b044fd3367c2133bc99166e1c19fb60ca00ade79350197abc0c", | |
| "model.layers.13.self_attn.o_proj.weight": "3a51d9fe98a222fd03bc911712e9eb9af5e8e53ea689d6ea47d3fdd0efc206b3", | |
| "model.layers.13.self_attn.q_norm.weight": "49366d1650fcab9d8fccb1630b54df8bc97e6d853bf5e68a2919c658eb3d36bf", | |
| "model.layers.13.self_attn.q_proj.weight": "9dc5a3c78f16286284cc7ba37e55522c359b1514ddcf52af98b198f94ec435f3", | |
| "model.layers.13.self_attn.v_proj.weight": "7896c5e46326f1080fcd2141477778039a95f6b963bcfc49c98c8460665c26da", | |
| "model.layers.14.mlp.down_proj.weight": "8d9c412061b970ede462c49cf8169fcc876a28a1ce6d541f763db282d157f8e5", | |
| "model.layers.14.mlp.gate_proj.weight": "4df3d4cc2936b0e635a892282123868c64550a32ba89a2ed0b584438f7d6409c", | |
| "model.layers.14.mlp.up_proj.weight": "fd39c8b17b7c3ee3d82df475ac9b9441f419dfa5b803faea8c5550a40ad5f10c", | |
| "model.layers.14.post_attention_layernorm.weight": "1451276cf944de90dc802826a5b9b82c960f01425dd38c0ea608194e758f8f7c", | |
| "model.layers.14.post_feedforward_layernorm.weight": "0744bfb4834be4bd99539af9f0b3ca5fe2f8d3fa355740a5ec57c0d3e30a1daa", | |
| "model.layers.14.self_attn.k_norm.weight": "2985bebb12dd03450adf28032bf28679c4f03b4c0fd6fda4a067329f29d42ae7", | |
| "model.layers.14.self_attn.k_proj.weight": "803fe0b68acdba7d9f38babc578099d4c3e7fca6ef50aba8f5503310ee3dc7f4", | |
| "model.layers.14.self_attn.o_proj.weight": "d2eb7783afbced9b23451fcc8e408fd0238acc6eeb101256d2e1258d4b6d20d2", | |
| "model.layers.14.self_attn.q_norm.weight": "5f290f4a7a726691d51cd0bfa17b49dc1627fe03aefeb01e43d709ac79adc148", | |
| "model.layers.14.self_attn.q_proj.weight": "191ae1055d119df1237b8489f55375a3d2fdef6bebdb05f9df08bfaab83f537d", | |
| "model.layers.14.self_attn.v_proj.weight": "32b70ae68f6555f49831c2162158487baf3bfea9fa89b5c95d3a93e8288c4d7a", | |
| "model.layers.15.mlp.down_proj.weight": "d2afb94bbfc20092dc6729db87a06e621a2b691182ec71fc730e5b363851a59a", | |
| "model.layers.15.mlp.gate_proj.weight": "9649b5fbda25c5186b118dfc096ef7f7353668755a40a659fa88c6c5bb40939e", | |
| "model.layers.15.mlp.up_proj.weight": "281971682d105e99d7415f2302e759cf2d746ee4dcc131bba4b50c7989014f27", | |
| "model.layers.15.post_attention_layernorm.weight": "f5f0b336794b17f363f0b721df3a63a4645a3677f3616d1141904b47d7dae365", | |
| "model.layers.15.post_feedforward_layernorm.weight": "5dbb53ee98977507f638e704717da154611feb975baf2b186dba01652a93f499", | |
| "model.layers.15.self_attn.k_norm.weight": "97f1418444e649b25c5beea83d959374a4f17ae2fa6891292fea3e13df11ea19", | |
| "model.layers.15.self_attn.k_proj.weight": "d12df558ffe8a6829ba14c2e56bfcc13afde793b10fa64d23c6f9dcbca23659e", | |
| "model.layers.15.self_attn.o_proj.weight": "f1ce6cb33aa04c4ac5fa3de736213fde9443789fb073a72803366335e42abcb6", | |
| "model.layers.15.self_attn.q_norm.weight": "79c1909b6c184e07b39b89abfd8c2bd7c4a92051ef4de7cd9b6e450c218a972c", | |
| "model.layers.15.self_attn.q_proj.weight": "f03efcda2dc5c78a909a389a30b510e82abd3f08a4a492ff2884e36fe9806e16", | |
| "model.layers.15.self_attn.v_proj.weight": "60b23e1326c3f3640203126c62f6c5220261f241dfc568009ad01ca8bd8d63be", | |
| "model.layers.2.mlp.down_proj.weight": "e36891d902249332dc708bddeb486ade3e63a41580060589229195d69eeafa55", | |
| "model.layers.2.mlp.gate_proj.weight": "fc38a7190cb3c78b25042caa484be05a4dade15b4245396a277d27d9726e8ed3", | |
| "model.layers.2.mlp.up_proj.weight": "b6c6b244284e6f6f65d2c220fba9c4bad7d382c6892618a47155f074fab08950", | |
| "model.layers.2.post_attention_layernorm.weight": "d7a4aef99d53fa2c15a7cfd9291cb2500ee5158fc768cc0e0dc40bb9cb3de3aa", | |
| "model.layers.2.post_feedforward_layernorm.weight": "a0b13d17e8c309ccb016d7995514524dba46ee452eeb2abaf8822a08b3d5a6ea", | |
| "model.layers.2.self_attn.k_norm.weight": "46599f1868d27aa95693d0c48349cda482bae9c5178cc79b5b26aa476b09bcae", | |
| "model.layers.2.self_attn.k_proj.weight": "942fc6349c713102d8a9a63335db8dbf94420b5ec95fbde718515c5d17345e35", | |
| "model.layers.2.self_attn.o_proj.weight": "5c3444c082d7597da94e69c548b8bd59287eaea7403a766eaa822aa570495664", | |
| "model.layers.2.self_attn.q_norm.weight": "2e05759c86f178156612ce7b886e774b173cb5553fec00164a689dbcd3a5027a", | |
| "model.layers.2.self_attn.q_proj.weight": "b99e755af205cac33d97bd4daeda701a910f337e0aee8ce206b86c8f45c68958", | |
| "model.layers.2.self_attn.v_proj.weight": "5bb3e5edd3c74facc1ab07816432d1872b66bc546e83f8be8deecb057d7dccf1", | |
| "model.layers.3.mlp.down_proj.weight": "3da6612a95b34a36cea1942da748c76adf9584a7bc57bf8ba094ac0a42db595f", | |
| "model.layers.3.mlp.gate_proj.weight": "beb6e75358152d316136c59bc69c7dbe1fe8b76a8880b1a5f773465b7381ef1f", | |
| "model.layers.3.mlp.up_proj.weight": "6a1450eaf87bb0397bc081696805d513430a285f1b3dbc5e2af282907a384abd", | |
| "model.layers.3.post_attention_layernorm.weight": "af0a62abfda5ae673f4826704bcf7f114dfba134b9b7e6f49f32db5be98919d7", | |
| "model.layers.3.post_feedforward_layernorm.weight": "8404ff9cdeb128df8466a06a93be2c8f635499b889145b8ae3d4c565ae4c3c86", | |
| "model.layers.3.self_attn.k_norm.weight": "9e4c0c0fee70c2600fb8ca7103cf5ac76d1f2ec6dd6d4767459b6b02f5e5e8e9", | |
| "model.layers.3.self_attn.k_proj.weight": "55cb30c4fadf9ea794db29e36ad58b4e3d8a4fb5f7211d90261a166aa81b0373", | |
| "model.layers.3.self_attn.o_proj.weight": "2beba007d502b4f5125df8f375c14a017707243e0cea4e09fbd8fa2c4f473ea7", | |
| "model.layers.3.self_attn.q_norm.weight": "09dc12655165944ef602b69190d1f2ac3d779ecf6770f574f2015bbebb125b97", | |
| "model.layers.3.self_attn.q_proj.weight": "4e8b5a72076b31a9101df9c13780585bac843539d3930ef0f7107fa9a8879d52", | |
| "model.layers.3.self_attn.v_proj.weight": "74c354b32a258d40c0bf9c10ed7aaca1fa3507e8f5e58f7c142acfeac74830c8", | |
| "model.layers.4.mlp.down_proj.weight": "a5666690a970b073b6a3e41233e9d80b0cfafb88bfab7db91296bc1b65239c59", | |
| "model.layers.4.mlp.gate_proj.weight": "feeb648c1076e51be283f0ee90b5cdd1a127c41c7a6f8a88980e7bdf8b4986d1", | |
| "model.layers.4.mlp.up_proj.weight": "5d0a6dd119324b2f49f4a058c2934c82273e5244ced3edce8087bb3a1771c414", | |
| "model.layers.4.post_attention_layernorm.weight": "164ab9e8837a4386568127fbd97b673eb4db6ab7ac62ff06dd068ec5c358e082", | |
| "model.layers.4.post_feedforward_layernorm.weight": "3e4252e6fa90ac72b6525bde4a9f1b642b14ba4e49b208b0c93a7dd6bd23a50b", | |
| "model.layers.4.self_attn.k_norm.weight": "dd68c79482029ca73ff461a6780a30dc8f78b5bacd3f8505d11bbb2a69709506", | |
| "model.layers.4.self_attn.k_proj.weight": "4c6eff55e4a313c096035aef5fe3e30447637308884b8c7be6c05817585d2e03", | |
| "model.layers.4.self_attn.o_proj.weight": "f0dfebe30aac0c790c4a89b42a640753d41df6d9fbe15c773863366f5c96589d", | |
| "model.layers.4.self_attn.q_norm.weight": "57c97ba948328f1ac8e4c4300a9906dcbbf13bc51496d11515ab7eeb7b26f7bf", | |
| "model.layers.4.self_attn.q_proj.weight": "d6a3ad8afb8f46135d9ddf68ca76a8df02d9b17f8674e7e044fb1cb0dc49ab96", | |
| "model.layers.4.self_attn.v_proj.weight": "33fa11272e92db34c6edc18ecae2e09b85f7c2506cbc70a4b9f78f8fe1a66699", | |
| "model.layers.5.mlp.down_proj.weight": "b1cde3d5a6cae7946efb41e53fffa4778cbb8a1182e5856fa6372becc254d5ec", | |
| "model.layers.5.mlp.gate_proj.weight": "bc6919033b6952830e7a735d3c269fb051841fe2cc988ed512035d13cf82d462", | |
| "model.layers.5.mlp.up_proj.weight": "d9e6b07b4b91b23535400a41cc8f7b1a4403ecc7e3f03684107cb98d66f41688", | |
| "model.layers.5.post_attention_layernorm.weight": "7f1dd764629865e973f0ee06eb3f63f4cdce9ce51a2147ff8ca519c20a5974d6", | |
| "model.layers.5.post_feedforward_layernorm.weight": "7cf7046630a5e956500fcd08a99a948e2793cac6885bbb391582c01f3980d6d8", | |
| "model.layers.5.self_attn.k_norm.weight": "5507450b8c188ed88e27c0db05826cb52dfe386f7c0150ed7dfa3a2781b04937", | |
| "model.layers.5.self_attn.k_proj.weight": "83a6fd49b99f632ad0a48d2b59f2e39d80921e28545087e73dc6c32a9d983652", | |
| "model.layers.5.self_attn.o_proj.weight": "98c1253e198055fbb67e75962dc41aaef1d5b5a9f1d62c57507b5ffbe038fe4d", | |
| "model.layers.5.self_attn.q_norm.weight": "681f6d5071bc7ad31868c78ba6043a46eba96d25cd2aa63b7ad293b0ca120cfa", | |
| "model.layers.5.self_attn.q_proj.weight": "4cfabe32053a6cc7c094e7ebbef549d70f847c0b09cf2b163bbc89f80ac041c5", | |
| "model.layers.5.self_attn.v_proj.weight": "bb4ae6fc9487faeafa13b00113184a5fed89089c6721a65075c9768df8cb4904", | |
| "model.layers.6.mlp.down_proj.weight": "db2990697f9d880d108187d23659423d089f3272ea8feaf7791003fef42e3fd1", | |
| "model.layers.6.mlp.gate_proj.weight": "05f7e552f316c84436dc8f7a83a92e3f7a94de7c1c8ac9adf03b010de258a22d", | |
| "model.layers.6.mlp.up_proj.weight": "09e2593f772b56f05103bddd39ccd1977e4c231ec0324bddbf25f99b246f68b5", | |
| "model.layers.6.post_attention_layernorm.weight": "02a2f1bb6e32a65d0194ece3313a3f2bfeecd7fff88d0ed0539bf02f9db819c6", | |
| "model.layers.6.post_feedforward_layernorm.weight": "3efc94fa918956e9e75c71a139500bd20d2a0a2247af062bf7ecfe06271ad2f1", | |
| "model.layers.6.self_attn.k_norm.weight": "cdb4a7d4556ba1f6016352646eefe20eb32a4d3545223ef86b8d8bd95805838e", | |
| "model.layers.6.self_attn.k_proj.weight": "b756085554b2fbcff6c55c4dd3f56ad3053d17158b89baebb141dd47af6696b8", | |
| "model.layers.6.self_attn.o_proj.weight": "98a241a7beddbd302385b3d72f7c76d29e7da2d7a54091331b49cee40d25c29f", | |
| "model.layers.6.self_attn.q_norm.weight": "e320d4085f33aac18a2a3b295797f75b74fb74a7098d2c10e9f64e270b396840", | |
| "model.layers.6.self_attn.q_proj.weight": "e6b6ecf7054d35c7b144a209f84fc1813bfe087165a1390c9818c9d322bd8a19", | |
| "model.layers.6.self_attn.v_proj.weight": "d587ba9d543182ee22884653850e5c0e0507be07b8e1f7aa347025fcd74c6d88", | |
| "model.layers.7.mlp.down_proj.weight": "7f202457b8e7bad0ef35264061bb177da4fb9429dc42e185c7a0d2e3bdf92db6", | |
| "model.layers.7.mlp.gate_proj.weight": "17c6be801bd07cfbfd47552fff8decf6977e84cd7921781bdf5c0d6d847deda0", | |
| "model.layers.7.mlp.up_proj.weight": "76358d9611aee8d2658c50192c6d4b0fd90ff032757d450f81981b4c821f1c3a", | |
| "model.layers.7.post_attention_layernorm.weight": "df269ee593f49e2075b17b6a299552333561aa89caea056b6b504913df64b783", | |
| "model.layers.7.post_feedforward_layernorm.weight": "c2cfb991b546a9044bcbcad8220492cbb3a23c2882b489624a4fec75332f5f4c", | |
| "model.layers.7.self_attn.k_norm.weight": "3b00eb73388b7dce8d3d27f6fdcb307848b27ade36092fea8a1a10788d0c237c", | |
| "model.layers.7.self_attn.k_proj.weight": "556db951558a588ad88219552866b8ca2c67cee5f70bc43d50f1575dfc60069d", | |
| "model.layers.7.self_attn.o_proj.weight": "f4601e58b4637a90f2584137a466498bb0f778be3c2b814a41a7c7beb1ea45a5", | |
| "model.layers.7.self_attn.q_norm.weight": "568608ce5f0102a968c889339faac5459373d4d90d7a0bb093ed242e34cb25f6", | |
| "model.layers.7.self_attn.q_proj.weight": "c0d7e834a7fa5b621f20e1d76fd5741fd85da22be7efa4506b42e334223cc589", | |
| "model.layers.7.self_attn.v_proj.weight": "82c49b62e9e588c2f811e9e21c6217dad1a34e8d83b12cefa58bf55ba7e38ebe", | |
| "model.layers.8.mlp.down_proj.weight": "19247c063ecb42137baad324a69801d20ff81dd8a1325322a9d05d8fa2b522df", | |
| "model.layers.8.mlp.gate_proj.weight": "30723a4a50c79b26b426320b5a4e43601a65f655e1d821b29b5af58bceddeb1e", | |
| "model.layers.8.mlp.up_proj.weight": "f5f962286fded1098f1119236e85e7a19b4d3c01850fc8ae2d0364f8e431b74d", | |
| "model.layers.8.post_attention_layernorm.weight": "0442f6b37f747744f72ad8c85d65d11ed8a2e059e1c09b9a83222e5ee2088489", | |
| "model.layers.8.post_feedforward_layernorm.weight": "c93e3d27e5b69f0f8f5344350d2e3552612244aabe1193e1193da2c6eb75b3a9", | |
| "model.layers.8.self_attn.k_norm.weight": "7094f507142bc7ce71be345c5d95850c4961ee22b0a81b2cfbaa05a91121db55", | |
| "model.layers.8.self_attn.k_proj.weight": "b0b2d963ce6161be9c64db46fb9444c31e8d5a81eaf15ede3350c66c7e3c92ad", | |
| "model.layers.8.self_attn.o_proj.weight": "f22c9f66ff502e73bc9fe6d74b4f1d4bef5a17e26c204bc2ff90368e41350645", | |
| "model.layers.8.self_attn.q_norm.weight": "bb1a553b1b3f932b4fd7c198c95a4e4bba5e2ed3e9208dd0a14d83beeff7bdca", | |
| "model.layers.8.self_attn.q_proj.weight": "6c2b5ffd3c8f32fdf0bec2e9f9d45d3d4083c99ed29c98a38be1b673365a0b27", | |
| "model.layers.8.self_attn.v_proj.weight": "4a736923925bf13a8d968572bc0e285f9f38492647d1572d6889f0951e6d256b", | |
| "model.layers.9.mlp.down_proj.weight": "e354b390ea9c93e7fdd58eb50a18821ee44eed2ca35dbf12f56172a9627fe1e2", | |
| "model.layers.9.mlp.gate_proj.weight": "4fbf42e9a2f034d18307ca5eb4f84e23da419495b249d956c80acbfb55cf7016", | |
| "model.layers.9.mlp.up_proj.weight": "d400ddf0baea84c4b13d17eb5ee08151110b9aa24d217dc149861688b84458bd", | |
| "model.layers.9.post_attention_layernorm.weight": "e47cbfd8c8d606d1720e20df6458c7defe0a93dcf29f59736c257f40c21ee458", | |
| "model.layers.9.post_feedforward_layernorm.weight": "74ee47ae9ddb1206d08a63c7cfae78ab286173a2cf4b26e136dabe0e49de512f", | |
| "model.layers.9.self_attn.k_norm.weight": "e5c9d27250b0d183d7bb4b7d7d63630fe3a468b05040e7605f292f1997b550b9", | |
| "model.layers.9.self_attn.k_proj.weight": "3e18bc070e3944491dbec8250c0faae0ddf9009015eb9f83bbd8821170719d85", | |
| "model.layers.9.self_attn.o_proj.weight": "3f6196a80a35ec19aa305f55e7408f0693400f5b983e38a6b18f5eec0facef04", | |
| "model.layers.9.self_attn.q_norm.weight": "226e7e628ccb784a9880a818cf5def108e830fb5f820723ba471acd562fb8117", | |
| "model.layers.9.self_attn.q_proj.weight": "523b210b104306065d406f8255b5c95468adcf9f5d9abf87d7b136515adc934e", | |
| "model.layers.9.self_attn.v_proj.weight": "13ae20095c8d8e1c0192a19c12c6db73e31d8fa0e4fbc59a19749a311fb13de7", | |
| "model.norm.weight": "9bd73ec88645dd586608e19f1a3c36dde9fb54ff76caa75263cc0a7feadc8f20" | |
| }, | |
| "tokenizer_files": [ | |
| "tokenizer.json", | |
| "tokenizer_config.json", | |
| "special_tokens_map.json", | |
| "vocab.json" | |
| ], | |
| "transformers": ">=4.57.6,<5", | |
| "true_vocab_size": 100278, | |
| "vocab_crop": { | |
| "embedding": { | |
| "exported_rows": 100278, | |
| "removed_rows": 74, | |
| "removed_tail_sha256": "9478ec4d7366618d530922bea53340f7ff004f464119c3635b5a0a59457b3818", | |
| "source_rows": 100352 | |
| }, | |
| "lm_head": { | |
| "exported_rows": 100278, | |
| "removed_rows": 74, | |
| "removed_tail_sha256": "a7fc1d23f585afda17dc3a214975e453ec083a286f9b18c8e90b569dc79d656d", | |
| "source_rows": 100352 | |
| } | |
| } | |
| }, | |
| "validation": { | |
| "fc1_split_repack": "bitwise", | |
| "finite_model_tensors": true, | |
| "qkv_split_repack": "bitwise", | |
| "safetensors_reload": "bitwise", | |
| "source_key_coverage": "exact", | |
| "source_shapes": "exact" | |
| } | |
| } | |