CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Ling-3.0-flash-Fin
From: inclusionAI <huggingface.co/inclusionAI>Newsgroups: alt.freeweights.textSubject:

Ling-3.0-flash-Fin

Date: 2026-11-15Commit: a5b4afbSigned: 2DC28CC7B26A283B ✓

Text generation model with 127.5B parameters. Safetensors weights, 255 GB in all. Published by inclusionAI under MIT.

127.5B params255GBLing-3.0-flash-Finsafetensorspermissive
FactsParams127.5BSize255 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get inclusionAI/Ling-3.0-flash-Fin
# manifest sha256 d4486ecb8b09… · 255 GB · 77 files
$ fw verify ./Ling-3.0-flash-Fin inclusionAI/Ling-3.0-flash-Fin
From sourceHosted (signed)inclusionAI/Ling-3.0-flash-FinLast check: 2026-11-15 03:26 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Ling-3.0-flash.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
255 GB
Weights
255 GB (safetensors)
Parameters
127.5B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
77, each with a sha256
Publisher
inclusionAI
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: inclusionAI/Ling-3.0-flash

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.co2026-11-15 03:26 UTCpassed

Model card

From the publisher at commit a5b4afb. Shown as plain text with links; images open at the publisher.

Ling-3.0-flash-Fin#

Image: image

Base Model&nbsp;&nbsp; | &nbsp;&nbsp; OpenRouter&nbsp;&nbsp; | &nbsp;&nbsp; Announcement&nbsp;&nbsp;

Introduction#

Ling-3.0-flash-Fin is the first finance-enhanced model in the Ant Ling family. Developed by Ant Group with leading financial institutions and domain experts, it extends Ling-3.0-flash through continued training on high-quality financial data.

With 124B total parameters, 5.1B activated parameters, and a 256K context window, the model combines financial expertise with efficient inference for long-horizon agent workflows.

Highlights#
  • End-to-end financial research: connects information retrieval, evidence review, calculation, modeling, and report preparation instead of treating them as isolated tasks.
  • Source-grounded financial search: Prioritizes authoritative sources to deliver accurate, complete, and traceable answers; FinFIRST is open-sourced alongside the model to enable transparent evaluation of these capabilities.
  • Multi-document financial reasoning: reconciles reporting periods, definitions, assumptions, and conflicting figures across annual reports, earnings releases, regulatory filings, and research materials.
  • Valuation and spreadsheet workflows: understands formulas, actual-versus-estimate updates, cross-sheet dependencies, balance checks, scenario analysis, and editable financial-model delivery.
  • Research-ready outputs: organizes facts, analysis, judgments, and charts into clear, reviewable materials for further editing and professional review.

Evaluation#

Ling-3.0-flash-Fin was evaluated across FinFIRST, FinSearchComp Verified, FinCRAFT, Finance Agent, APEX-Agents, SpreadsheetBench, and τ³-Banking. These benchmarks cover source-grounded retrieval, investment research, long-horizon execution, valuation modeling, spreadsheet operations, and banking workflows. The model is competitive with both similarly sized models and substantially larger general-purpose models, with particular strength in source selection and tool-intensive financial tasks.

Image: image

Local Serving#

The current checkpoint is released in BF16. Because Ling-3.0-flash-Fin shares the same architecture as Ling-3.0-flash, it is compatible with the same SGLang and vLLM runtimes. For deployment instructions, see the Ling-3.0-flash deployment guide.

Important: Thinking mode is enabled by default. For optimal performance, we strongly recommend using temperature=1.0, top_p=0.95, and top_k=20 for general inference.

Limitations and Future Work#

As our first finance-enhanced release, Ling-3.0-flash-Fin still requires further validation in complex, long-horizon workflows. Key assumptions, valuation results, and investment conclusions require professional review and do not constitute investment advice.

Future releases will explore finance-enhanced models at larger scales to further improve complex reasoning and long-horizon task execution.

Training content summary#

The public training-content summary identifying Ling-3.0-flash-Fin is available below. Please refer to the document for its covered model versions, training-content scope, summary version, and update date.

This summary concerns training-content disclosure; it does not replace the model’s technical documentation, usage terms, or license.

Files

77 files · 255 GBWeights 255 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 77 files with their sha256
FileSizesha256
.gitattributes1.65 KBc3318272e9558ed2d973893d94ae51d1aea999132ee2437676d2321a143cf39c
README.md4.50 KB770e5e547d2f1e539a0f41a01231f0a9641c019550abc81891aba36ee86d02a8
assets/ling-3.0-flash-fin-evaluation.png484 KBd6d270a97c54d6216457e5a8dbf6dc490dd707602bcfb7f2ece3e5b02a5477b4
assets/ling-3.0-flash-fin-logo.png77.6 KB2a20fd18d1700a170b73e9a85c3a6dc3ebab3ca9f42417a9522aa7451d29f20f
chat_template.jinja6.09 KB2e2f382c127bceafc594ae32693410399af94ef33ec858e2fac3d758ea146b90
config.json2.90 KBf3e5b1ad82762c7910a303a3642290f0ac4d3abbc9046bf2eab6b19c0385aa05
configuration_bailing_moe_v3.py4.72 KBf2c048966aec8a2f042cfeb1351f74d51a28589b409c55baae7d24e841c1f6c4
model-00000-of-00064.safetensors3.93 GBa81bfacb6bf743c87257a9cce3c9acff4d6f58c49758095504f36dc3bba90035
model-00001-of-00064.safetensors2.26 GB0139ea63dfd21a6a1cb564b7ad06abe326d521f6671830cf163afca29f9c50ff
model-00002-of-00064.safetensors2.26 GB04236d570566aa838c4c948d2849cb869d3b3fb661d637d38350c08f1d16a83f
model-00003-of-00064.safetensors2.26 GBafe7c5fb9f927f38c6ff893f70be854715184681d6bc4bed4d8a038ea90f8fb7
model-00004-of-00064.safetensors2.26 GB01cc51c10a9a532260a4d9cd3e9ba35375ce19372cf54e5f58773f51198bd013
model-00005-of-00064.safetensors2.26 GBe93b24886b73714b8708cc7f05623e5f4f66bae97e1041fec893f50ef287d37f
model-00006-of-00064.safetensors2.26 GBbcdc8e97147556a38482ee9a36fe7131accf436c3e17b0997572f78c512777b0
model-00007-of-00064.safetensors2.26 GB8d9c5d605538cd49feed1ece40318903081043ceb2acff776018029a421b5167
model-00008-of-00064.safetensors5.31 GBd3bb1d4e0f29cf270db85a01d80f73a6318d159a3c4f29af4dad5901d3019020
model-00009-of-00064.safetensors4.53 GB30edf837954a765e59de08fa470d8062852cadffdff8851963a772da3497d7cf
model-00010-of-00064.safetensors4.53 GB86366804b92e7b0bccaa2809a990e50b1aec68bbf935caf63f63a7241b508408
model-00011-of-00064.safetensors4.53 GB38227dd83d4b215530f029ee2769d94cda7de8e6d909241cce1c93e309ec1bca
model-00012-of-00064.safetensors4.53 GB9e4d27f1b8179c35d3c221c2c2475d1278ae2ed7c95b82566949bc1e34e245a6
model-00013-of-00064.safetensors4.53 GB187f7eb2319b8d09cb376162cd1319a82b5008c195d3c4d064560966fde7ca4e
model-00014-of-00064.safetensors4.53 GB2b908e48a083d7f2e1e5855068dbebe18110b49a596432cec0f353797099a03a
model-00015-of-00064.safetensors4.53 GB6c51547b6de3d096683ee478f157a5ad2c3455ac6f686c60ad4f2e9147ba4036
model-00016-of-00064.safetensors5.31 GBb17259eee62388954db81fd534a831413502c199c6e56e657cc795f039dd21cf
model-00017-of-00064.safetensors4.53 GBaf779e978832b1a476e3fe387def4c4c30961b1d4a476e9140226d5b7e703ab9
model-00018-of-00064.safetensors4.53 GBd0da4aa400a314d5bd0878880be870e1940af74fba4d055322aea977e3c435fa
model-00019-of-00064.safetensors4.53 GBa2393209cae9ee5679163b2f024ca6757a3680c3a25e97c405e31d2f5c923488
model-00020-of-00064.safetensors4.53 GB3d6d5acef7ebdc618ead5ecf277590603258e871463fa9d9eca998acde654ada
model-00021-of-00064.safetensors4.53 GB5145246d64055f099d3c41651f247640413c0aec9c6afe0b70dcad1ef75cc808
model-00022-of-00064.safetensors4.53 GB311e8b00816f14ae739e828f35e1f60489b73d093c5da2e4aa0c3bc62f46c350
model-00023-of-00064.safetensors4.53 GB116fa4bfc4260d1eeadde431d997264667a18466cfccfd8398db9565e74d9e30
model-00024-of-00064.safetensors5.31 GB1ee32adfcf108acb07cdd9325f1a5758bcd897311c2c859eb6948f94c3ed3b66
model-00025-of-00064.safetensors4.53 GB0a3cdbe1a18b80ded81390281b2a696c1ce5fb9013a5ad451a82db849880740c
model-00026-of-00064.safetensors4.53 GB81be58b60d34ec5b34b7604cc4200e835ac01fb80a9179544c2cb7d3fd2d44b5
model-00027-of-00064.safetensors4.53 GBd287296d9dd149c90b7bbc8fb8e3b4d70a1b749c3717ebc69618fc9fb4c5d07d
model-00028-of-00064.safetensors4.53 GBdc757fc0123f041bc4da66ec9a00b5a68aeb348a01cc294779be3fc9a896bd22
model-00029-of-00064.safetensors4.53 GBb4f4a3e8c3ac6e66266cd95cf05a46b02dc47966618454141cc069d75a461deb
model-00030-of-00064.safetensors4.53 GBb75b92034f9ee4fd948a00c7b539da59827f288ce96bd1694f510696cd8d3e8c
model-00031-of-00064.safetensors4.53 GBf9c6b593607afe1f968eaa97501c4f993c2f2104a179fc8be010b198e1c9ae68
model-00032-of-00064.safetensors5.31 GB58d840df322c8308f9905acf6c488539f1d9a59dfe1b35cb0505076431225093
model-00033-of-00064.safetensors4.53 GB1f31fb5e50c636a25cab51edef07ff7c4a0577ed9402477e47ae67abdfff2ffc
model-00034-of-00064.safetensors4.53 GB01f4ca9cb72dbb8fad353da9ea8bb57b7c1da2bf6f9db88d2ed4d63993f5b145
model-00035-of-00064.safetensors4.53 GBdbef5fab631e4137ae99f37c32fbc55d86ed5b290850dd67c1f5a6ac4c769eb9
model-00036-of-00064.safetensors4.53 GBaf5529eeffb2d98ff0236a7562489bf43bb93f0c0257cffa61df72d9ae9d59c2
model-00037-of-00064.safetensors4.53 GB3715449b6b14b56f8b5e6717f583392fda269d59cf4d6fa122e797534d312437
model-00038-of-00064.safetensors4.53 GB91a9b3dfb7aec21fbe58d6b8c3085f95deae2b634e50d805c43cd04aa54822c6
model-00039-of-00064.safetensors4.53 GBd2aed6402076d3904dec753240256e65ad88e77d194c9058f843d77d3bd870e2
model-00040-of-00064.safetensors5.31 GB6a186a1cd2f54af5ccf8dc7febc1a8b3a4fff725514660a1adb8539298595049
model-00041-of-00064.safetensors4.53 GB1864cfd729470f4bd4d18cf852158274fb2283c4cfec39666fed0ae3b7a46a4b
model-00042-of-00064.safetensors4.53 GBabcd4a7c4468fae38cbdcec35b678d1b40b78dd327ca1cec51298f77ef1b697a
model-00043-of-00064.safetensors4.53 GBf94f21dba9fb6f2117f50a97ccbbaeac977169af5b3f910e8b3a2387492394f0
model-00044-of-00064.safetensors4.53 GB918e23543c9ca39a1f011fa861f9dcd34af34392ea72b0c41d54baa88b116226
model-00045-of-00064.safetensors4.53 GB4d20b7ea65f3563c0bad8261501717690ff5b2a50a4dfd6b9c926e4735ceca37
model-00046-of-00064.safetensors4.53 GBf7a9194d22e7774d64d9f880b2ab9298b3438d8a8610d77adaf7408ee3eaae69
model-00047-of-00064.safetensors4.53 GB1facb4cb18e5a39a348c9ec53f5f9b3bf48fff983c160070fd217102a8c4f135
model-00048-of-00064.safetensors5.31 GBddfbd0199e0b1d28313a7deb7917ca7a33add97aeb44b54a9d99a6b794339164
model-00049-of-00064.safetensors4.53 GBe262175cc58788c2696f3740ad44490fe67bf7671b06510bece6e8d5d8133dd4
model-00050-of-00064.safetensors4.53 GBfe9ffc42b9a80abbf573f2719408a34267daea64ffc2744de80136996da095df
model-00051-of-00064.safetensors4.53 GB1b67b918ec89e29f70d2d32afd79e946e0017efb2703bdb756890bd06d8712b4
model-00052-of-00064.safetensors4.53 GBe98782c620cc512eba7cf581049c79e9ed8c2fad123c7d8a9ec1162b062a017e
model-00053-of-00064.safetensors4.53 GB9c8c1bd6c2207447a8a50aeaff9252e934604ac5a5d0260a45ed1955260aefef
model-00054-of-00064.safetensors4.53 GB6c76948f8dd9af2aef6d4a83c2810d26fe98823b4893fa134a5d77f0c7d2b4dd
model-00055-of-00064.safetensors4.53 GB3ddf600e563d6982c6f9fb49f32ea4b2bc91a8b93dffb55f0af2043b7bcddb5a
model-00056-of-00064.safetensors1.64 GB9ec351335e74964c6496adac6a3f86a62894e90b43ae95d8a8de6bedb8d413a7
model-00057-of-00064.safetensors755 MB061bb7eeb28095601e70567f7f929dfeb80b889f3b68db5f7a5174de865f4326
model-00058-of-00064.safetensors755 MB83479a610d013f61e4ef6c910d1b4c836f6702e5c156956f241bd5e1e4964c0b
model-00059-of-00064.safetensors755 MB7c2e2797e466873e9d166134ae5e0b06f26c0ec558bbd84990b31c65ecb94aad
model-00060-of-00064.safetensors755 MB0d40e7dea9caa8ee1a6772f15c09ab31fc93477daa695705dc8cf22721e270c1
model-00061-of-00064.safetensors755 MB8d6726bad79318d13a7c564b57b423c1843229adfdd0473b3dbfb379cfcc27d7
model-00062-of-00064.safetensors755 MBd43f39bda324ec6eee04873ee3bdde5b1050107a9294d96fe53fdc192716631e
model-00063-of-00064.safetensors755 MB8b73445b65ac533a92e9190dbc7630b3b4b563c446c16b0445110f840d2808d3
model-mtp-00001-of-00001.safetensors6.14 GBe6d6ce5b0cbb785739f6baa6fee414443bcc81eeb2c17e667f2e4b3b98097b83
model.safetensors.index.json5.80 MB19b4f2f2e199c7e34bab049c1fc1d99b1661700a669a9ea7e7fabcb4527c5920
modeling_bailing_moe_v3.py73.2 KBc2509bf7ac580c262e2581d34d6403aa21682d2e10beb9ad85ad8820a7e33a40
special_tokens_map.json580 B69b63b9f81044ead642d16a5fdc01bcc737dc1183746485c8397ab14d3126614
tokenizer.json12.2 MB40fb9d7d7795b8bd305aeff39ce9963f3f450915b9553f2938e009be9a1fed60
tokenizer_config.json49.7 KB2456b0372956cd3e82f17e33372148b115a94970bfd4878ba5e7e60cd3204f74
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
a5b4afb48f pinned now2026-11-15 03:26 UTC77 files · 255 GB

Use it

$ fw get inclusionAI/Ling-3.0-flash-Fin
# manifest sha256 d4486ecb8b09… · 255 GB · 77 files
$ fw verify ./Ling-3.0-flash-Fin inclusionAI/Ling-3.0-flash-Fin
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/inclusionAI/Ling-3.0-flash-Fin.json --dir ./Ling-3.0-flash-Fin $ python3 fw.py verify ./Ling-3.0-flash-Fin ./inclusionAI__Ling-3.0-flash-Fin.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download inclusionAI/Ling-3.0-flash-Fin --revision a5b4afb48f526175991724472c179e5a065604de --local-dir ./Ling-3.0-flash-Fin
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("inclusionAI/Ling-3.0-flash-Fin", revision="a5b4afb48f526175991724472c179e5a065604de") model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-3.0-flash-Fin", revision="a5b4afb48f526175991724472c179e5a065604de", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve inclusionAI/Ling-3.0-flash-Fin --revision a5b4afb48f526175991724472c179e5a065604de
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
770e5e547d2f1e539a0f41a01231f0a9641c019550abc81891aba36ee86d02a8
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: inclusionAI <huggingface.co/inclusionAI>Newsgroups: alt.freeweights.textSubject: Ling-3.0-flash-FinDate: 2026-11-15Commit: a5b4afbSigned: 2DC28CC7B26A283B ✓
Upstream
inclusionAI/Ling-3.0-flash-Fin
Pinned commit
a5b4afb48f526175991724472c179e5a065604de
Manifest
Ling-3.0-flash-Fin.json · .minisig
Manifest sha256
d4486ecb8b09dcdaea05068af718dbd55c59a09476d4892ce390d0e6a58fdcfe
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:26 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/inclusionAI/Ling-3.0-flash-Fin.json $ curl -O https://freeweights.allternit.com/manifests/inclusionAI/Ling-3.0-flash-Fin.json.minisig $ minisign -Vm Ling-3.0-flash-Fin.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

Model tree

Parent

inclusionAI/Ling-3.0-flash · this model is a finetune of it

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download inclusionAI/Ling-3.0-flash-Fin
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Ling-3.0-flash-Fin.json. Provenance. Takedown history: none.
Source
huggingface.co/inclusionAI/Ling-3.0-flash-Fin

Variants

1 quantized or adapter build of Ling-3.0-flash-Fin. Each has its own license check and page.

SubjectSizeParamsLicenseDate
Ling-3.0-flash-Fin-GGUFHosted (signed) From: bartowski in alt.freeweights.text2.02 TB—Permissive2026-11-15

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B