CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-V4-Flash-0731
From: deepseek-ai <huggingface.co/deepseek-ai>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4-Flash-0731

Date: 2026-11-14Commit: 7872f01Signed: 2DC28CC7B26A283B ✓

Text generation model with 304.2B parameters. Safetensors weights, 167 GB in all. Published by deepseek-ai under MIT.

304.2B params167GBDeepSeek-V4-Flash-0731safetensorspermissive
FactsParams304.2BSize167 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get deepseek-ai/DeepSeek-V4-Flash-0731
# manifest sha256 8ca633f5c868… · 167 GB · 74 files
$ fw verify ./DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash-0731
From sourcedeepseek-ai/DeepSeek-V4-Flash-0731Last check: 2026-11-14 06:28 UTC
Runs withvLLMSGLangFine-tune withAxolotlTRLPEFTUnsloth
OverviewFilesUse itLicenseProvenance

Overview

Size
167 GB
Weights
167 GB (safetensors)
Parameters
304.2B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
74, each with a sha256
Publisher
deepseek-ai
Added
2026-11-14
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 06:28 UTCpassed

Files

74 files · 167 GBWeights 167 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 74 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
LICENSE1.08 KBf2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
README.md7.24 KB252acafdc9204d0dba3fde1b0a93d71cd1664a4ceadfe222b60117ed0ccc56ff
config.json1.89 KB6c8f3d2d3b48707541b88f32f22ef3f0f8a6b57d8523281e2b8d3cdb0ae9a023
encoding/README.md9.17 KB294ed6493ebfe5a487f172154d60c494899997fed8806fdd3352dd8e3c33f9de
encoding/encoding_dsv4.py29.0 KBabc0d26120250dda0ae077dc64aa28836026e61e970854aaeb792445e6a0dde6
encoding/test_encoding_dsv4.py3.74 KBc2bc54c4c934f5c64096bd9c555efa7d1ddf179c1eff58f01ceb2dcd60adcf28
encoding/tests/test_input_1.json2.75 KB10e0c074c977c3a80daab758af28219c6b1c2bd7f3f5cf2890c84b361cc32897
encoding/tests/test_input_2.json526 Bc44ae0db20fafff38a6021e8068d7ed6e28605d76cafd20be80b03398509f447
encoding/tests/test_input_3.json4.55 KB37bf8ef95e0411ea5f411be0b02fbafec7363438b6ccefddca0c52ec9aeaf69a
encoding/tests/test_input_4.json2.73 KBc45bbd0a1b7a2f75033d8db4ba74ee5b7653bd01114045a52f79d3b387663465
encoding/tests/test_output_1.txt2.39 KB9b366d9d2eac842a6e890594aac0b58648e5623717202b33497afadf03e26540
encoding/tests/test_output_2.txt342 Bca66b01a1ac3a204bb032c928fb607d4877171e998a50f7f89f39fa821b75665
encoding/tests/test_output_3.txt3.31 KBb3b1cd8748b7b90d3c6be6da3f786f12e4d70be073bd445ea162dfad4dc01a64
encoding/tests/test_output_4.txt2.55 KB60e1643840ba9e4aeede450feb7b0498fa66ee24e4a939d48855ce04ec6fc375
generation_config.json170 B5fccff80f55a4d455bbe516bdd552edf3e9623df95e99fbf2a3c3389fdf91af0
inference/README.md951 Bb9fe8027f91f2160b46582b61eaaf7b9873b3da36ee9f98bc76a900e7c1fed94
inference/config.json1.16 KBc90861f3d10a9e4ef5954f8f1a34c529d480da1c5799f84660028f4e38e14e71
inference/convert.py6.64 KB6efe65ebc66b18c9f2656816608f941cacfe20da79c2dee19040ecbee8b42bfe
inference/generate.py5.80 KB775fcfee2344e21a7b02c73161c517763e4348b84cf2eb266353e0857b9c8812
inference/kernel.py22.2 KB59b325083d7103975cba025bd0d60ea343bb82d8fff53088afb7c04bd380c0c2
inference/model.py45.1 KBc0c19e6c9fa439bac7fbb1c5bc1868232dfd5aa2f439a548d0e33dcc2a9edd3f
inference/requirements.txt92 B857e0b8b58e41cabe16e55bf4ab7ff791677c53b25f0f3e104ef85227cd11eab
model-00001-of-00048.safetensors1.06 GBf3668ba4cccf1ca6a7eb84e888fb92c1cdc7204d472ba9db771e6fd3abf6b874
model-00002-of-00048.safetensors3.57 GB77b26c939a0e25b3113c8d6bb04e1901a748bd4a7d2589e3bfdaabdf1e9bba14
model-00003-of-00048.safetensors3.57 GB412abf4c906faadc221ef0cb50f90fe20bde8454a08ad4dc2364b6b79e7fda5c
model-00004-of-00048.safetensors3.60 GB9610f56bc587fb0ff9a8b68a60299482ee8c433fe5b5587e4257aca98add4a2e
model-00005-of-00048.safetensors3.57 GBf87a5ac7b8becc31f9c3169afd3a6f33fb82b4af9e21022e3755a10bc28f0180
model-00006-of-00048.safetensors3.59 GB4a4f3764e3fc772b9fba67f0a44ef68e18f178b6f00faa80b75db549e51894cd
model-00007-of-00048.safetensors3.57 GBdf81bb80e27a689e01fa579eebd6499f86e0b6105f7fea18961aa5eebbbee9bc
model-00008-of-00048.safetensors3.59 GB224968d2b27f8669365ec08657a768dfec40da0585f85f302a31495931f6a526
model-00009-of-00048.safetensors3.57 GB04d69ef1071fff8721c62968c200a5583122b59b015e9ef9b2978bfed271b2b7
model-00010-of-00048.safetensors3.59 GB627145f4ebeb1cc3f5bdd03416b8cb7370b3c96974853cbeb8e5516ad5713e49
model-00011-of-00048.safetensors3.57 GBe4b8e601dcbebe902e0102e7b098b670a121cb8b9564dd719fc41d782c8416e0
model-00012-of-00048.safetensors3.59 GB64ed4e5f6126ba029c462c9d5fca0fc907c5f855b4ba01194d79560f6db16e42
model-00013-of-00048.safetensors3.57 GB8dfe199d07c07ddd141c2c0136a2237f1161250a1a03ebe8deaabac93440da1d
model-00014-of-00048.safetensors3.59 GB45db2f540f825f92453c50335e49aede58cca56bc578d1787c12a0fbca6593e5
model-00015-of-00048.safetensors3.57 GB5810381a0f05b7381c002d299ed6ac19e42eba8070dd17e2703546944d84f292
model-00016-of-00048.safetensors3.59 GBe0530b7024771b0ce2df9b40bcc2232578f3300178487ec216863b0b2835617b
model-00017-of-00048.safetensors3.57 GBed11130247118b185ade893c0109bad896dd394cb1e066ce4fce044176261d94
model-00018-of-00048.safetensors3.59 GBe393fea96da2a3414ef089354fc32e1c8891954de40958c84d2c2ecf80365b25
model-00019-of-00048.safetensors3.57 GBa74ca4d3e8e82ce20c458bb8b1900110b753793ad4c58d08f38995f719c616f7
model-00020-of-00048.safetensors3.59 GB9f556769926e60309e8defe45ab59fc8b26ae460d30c190cd746a3d78c11e2c2
model-00021-of-00048.safetensors3.57 GB1671cce7f90d781f796b5ca6bf32dd1aeb740abcb2735e41ffd28f62485ce005
model-00022-of-00048.safetensors3.59 GBdecd67a4bd97a75fa36861d2ad3067afeefa6a04a20da997fe6c19f171e70132
model-00023-of-00048.safetensors3.57 GBc61a3e179cdbee19bfb8cbc4e111928ce2f1e1f0f4729d7c0cd5634354a4689d
model-00024-of-00048.safetensors3.59 GBfc27aeb4233534f6f7781dcfe57127a3908ae10fc025c5d86dc0682057f8b2fe
model-00025-of-00048.safetensors3.57 GBa66b6b8d5821b68f5b511e4f91e12025cd07d0fa6d0b71e722d825a2d6d878ca
model-00026-of-00048.safetensors3.59 GB657b89314fbaf6eee4acce24b3baf7e5fd2c5986a96ad85b08d90539cde869fe
model-00027-of-00048.safetensors3.57 GBfb01f21a0da0446b0bdf25a127ab19a6b06006acd8735f06a9ebfe34423fd7f5
model-00028-of-00048.safetensors3.59 GBb2fd5cbbb639f16e673bc484e5cca16b52a58bf2ab4bd62592e0c5408712ad7c
model-00029-of-00048.safetensors3.57 GB9ec2fdf900275daeac0980490c5c731cc7868b151ce1de5698f48418de4fa5f0
model-00030-of-00048.safetensors3.59 GB9ed3c317bf967d32133ad3a068ee4c56aae9784bc8b7da694482437f37dc1782
model-00031-of-00048.safetensors3.57 GBd5078c3fca3e6370043606ead7856e0b8fe67a9aab52c415769f29934c4d7f5d
model-00032-of-00048.safetensors3.59 GB163653848f002718d3deaa6ce48885483fc1f2e12e50e44a47477c73ccd91393
model-00033-of-00048.safetensors3.57 GBf2cffd43f2a5f491f4691f8694e6bc08239158e143ae7063dc04f0eb0259214a
model-00034-of-00048.safetensors3.59 GB0f94945121474cfdb6a9ab175914d3811ffbf08e6cc54082e14e473c755d18d8
model-00035-of-00048.safetensors3.57 GB9cb6a316989f7c7385e3ec2bd42ffe766ee126c70ef3466742849982ee1b0f0f
model-00036-of-00048.safetensors3.59 GB7e6761421fe944c2143eb897b983085891b421c148c6c17fb5cd8eaa9bdaa497
model-00037-of-00048.safetensors3.57 GBa59d662f1143596d56c452a1230b717ce43edf678207398c573a2503b0f72c91
model-00038-of-00048.safetensors3.59 GB137fa617a74ba8e73fd76bb1010c7a85d791aaa150006cb66faa04a83e9e730f
model-00039-of-00048.safetensors3.57 GBa29af1aa519d7ce726235ea2c2b38146d756290cda7a82d90c4d4438155b53e4
model-00040-of-00048.safetensors3.59 GB8bc93d8a7d1987dc86b14e22b1d8f42ec31da92c56edd9f312daf43f33a6a206
model-00041-of-00048.safetensors3.57 GBfd312e7fdd6cb5796df356a7f0314f124851dc149991e9fb02c5bed45cc4ba05
model-00042-of-00048.safetensors3.59 GB4d19bf368083c9a183cb0849f316ec17b62f859ca824c0586e779657efb6e6a6
model-00043-of-00048.safetensors3.57 GBb7103842ceb70848f9804f55c193d6a57f43174a587cba42b61b5c1bc4e1303d
model-00044-of-00048.safetensors3.59 GB422d3889fa20c238b7f97464c14df0bcf3328f189c294f41a3a334421dc560c7
model-00045-of-00048.safetensors1.06 GBa5be6aed7b84fc87ec42b5d24ba0b0d67f253a3906fcd99c13f4f7be5958fc00
model-00046-of-00048.safetensors3.61 GB5db924ca907e0d93acd975bd5079c3662717f9ac709f23d079bd8f816d29d9dd
model-00047-of-00048.safetensors3.56 GB62816173f9f6e136b20b48e3b6f16613ac9ea02b5603f636928b253244a548bd
model-00048-of-00048.safetensors3.69 GBcc43742bd24ae6bcdea343a91442f6f66aed2cfebcc6b235470204851ce2f8a9
model.safetensors.index.json5.60 MB98efab455cf08dfbbbaaba6f570e1bf10bf927d2b4c3c453a59c2f6f0e3be92b
tokenizer.json6.37 MB8f9f37ca37fdc4f5fd36d5cf4d3b0e8392edb4e894fd10cc0d70b4957c8633cf
tokenizer_config.json801 B6ac8c8dc065ed118161d02dd532749ae3f52c243deac27872134fae2f50d8547

Use it

$ fw get deepseek-ai/DeepSeek-V4-Flash-0731
# manifest sha256 8ca633f5c868… · 167 GB · 74 files
$ fw verify ./DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash-0731
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V4-Flash-0731.json --dir ./DeepSeek-V4-Flash-0731 $ python3 fw.py verify ./DeepSeek-V4-Flash-0731 ./deepseek-ai__DeepSeek-V4-Flash-0731.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download deepseek-ai/DeepSeek-V4-Flash-0731 --revision 7872f01b1d1fe23eabc4c98b48bffcef5a386062 --local-dir ./DeepSeek-V4-Flash-0731
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Flash-0731", revision="7872f01b1d1fe23eabc4c98b48bffcef5a386062") model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash-0731", revision="7872f01b1d1fe23eabc4c98b48bffcef5a386062", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve deepseek-ai/DeepSeek-V4-Flash-0731 --revision 7872f01b1d1fe23eabc4c98b48bffcef5a386062
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Text in
LICENSE
Text sha256
f2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: deepseek-ai <huggingface.co/deepseek-ai>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-V4-Flash-0731Date: 2026-11-14Commit: 7872f01Signed: 2DC28CC7B26A283B ✓
Upstream
deepseek-ai/DeepSeek-V4-Flash-0731
Pinned commit
7872f01b1d1fe23eabc4c98b48bffcef5a386062
Manifest
DeepSeek-V4-Flash-0731.json · .minisig
Manifest sha256
8ca633f5c868d4c08386ace665a494ca30aac55a9578f5596949cb04c89debf5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:28 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V4-Flash-0731.json $ curl -O https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V4-Flash-0731.json.minisig $ minisign -Vm DeepSeek-V4-Flash-0731.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download deepseek-ai/DeepSeek-V4-Flash-0731
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-V4-Flash-0731.json. Provenance. Takedown history: none.
Source
huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

Related models

All of alt.freeweights.deepseek →
From: unsloth <huggingface.co/unsloth>Subject: DeepSeek-V4.1-Flash-1017-GGUF
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: DeepSeek-V4-Flash-0731-GGUF
From: deepseek-ai <huggingface.co/deepseek-ai>Subject: DeepSeek-V4.1-Flash-1017
From: ISTA-DASLab <huggingface.co/ISTA-DASLab>Subject: DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF