CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / NousCoder-14B
From: NousResearch <huggingface.co/NousResearch>Newsgroups: alt.freeweights.textSubject:

NousCoder-14B

Date: 2026-11-15Commit: bea2709Signed: 2DC28CC7B26A283B ✓

Text generation model with 14.8B parameters. Safetensors weights, 29.6 GB in all. Published by NousResearch under Apache-2.0.

14.8B params29.6GBNousCoder-14Bsafetensorspermissive
FactsParams14.8BSize29.6 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get NousResearch/NousCoder-14B
# manifest sha256 d9657593991e… · 29.6 GB · 17 files
$ fw verify ./NousCoder-14B NousResearch/NousCoder-14B
From sourceHosted (signed)NousResearch/NousCoder-14BLast check: 2026-11-15 03:45 UTC
Run at homeGet help

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

Fine-tune of Qwen3-14B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
29.6 GB
Weights
29.5 GB (safetensors)
Parameters
14.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
17, each with a sha256
Publisher
NousResearch
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-14B

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 03:45 UTCpassed

Model card

From the publisher at commit bea2709. Shown as plain text with links; images open at the publisher.

NousCoder-14B#

https://x.com/NousResearch apache 2.0

We introduce NousCoder-14B, a competitive programming model post-trained on Qwen3-14B via reinforcement learning. On LiveCodeBench v6 (08/01/2024 - 05/01/2025), we achieve a Pass@1 accuracy of 67.87\%, up 7.08\% from the baseline Pass@1 accuracy of 60.79\% of Qwen3-14B. We trained on 24k verifiable coding problems using 48 B200s over the course of four days.

Image: test Image: test

Acknowledgements#

I would like to thank my mentor, Roger Jin, Dakota Mahan, Teknium, and others at the Nous Research team for their invaluable support throughout this project. I would also like to thank Together AI and Agentica for their immensely helpful blog posts on DeepCoder-14B. Finally, thank you to Modal and Lambda for their generous support by providing me with credits.

Files

17 files · 29.6 GBWeights 29.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes1.69 KB41a42e146a76b121406519030bc9174086d613f781b30a427d4b5c1d09754fe0
README.md1.44 KBcd84dcec0554561979278f539f54832c49040ef1ea14b2e732235bcc959209cc
config.json819 Be89f89500de6c5d615c098b85743796b5c59d050ea148603836935778bafa03e
generation_config.json239 B2325da0f15bb848e018c5ae071b7943332e9f871d6b60e2ed22ca97d4cb993d2
lcb_score_vs_step.png246 KBa87c7125a32f4112bdcd2bcc53ef43e1692b7b889ab480a9b007baca1dcf554d
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00006.safetensors4.98 GB2dd801475ef2e8120ea91ead3af07423bdd2c1cb14c722a59e231468c277d929
model-00002-of-00006.safetensors4.98 GB12e3d75adc67b95bab27030b2ac65f516572295e0568068384147f48fa234ed4
model-00003-of-00006.safetensors4.93 GB1fda3faaf8dc319d553e0569da25328101ece42101700d8c873d051b7e11f1c6
model-00004-of-00006.safetensors4.98 GB7124dab9a9de4aff05216f45f520850cff80f90b26b45ec13337fd68b03bb311
model-00005-of-00006.safetensors4.93 GB06115f9ff8444cd6cbbb6080bd949b3a626b9da24f0ac4af509d7c5820ffb621
model-00006-of-00006.safetensors4.73 GBc6e3ec666831370fab98d3dc4ca811beb91b3367a55cd0d94526cac3c68fefab
model.safetensors.index.json36.6 KBaf9cd4e3bd21c994f831887e4e68f68ad2b1572e92db87e5aa4f8e5c3af83aa6
performance_params_ratio.png346 KB0eeb5b023b4fbee2d6670f61541a2544a85b7965c84c066cd277a44398bd6ede
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json9.73 KBd5d09f07b48c3086c508b30d1c9114bd1189145b74e982a265350c923acd8101
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
bea270969f pinned now2026-11-15 03:45 UTC17 files · 29.6 GB

Use it

$ fw get NousResearch/NousCoder-14B
# manifest sha256 d9657593991e… · 29.6 GB · 17 files
$ fw verify ./NousCoder-14B NousResearch/NousCoder-14B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/NousResearch/NousCoder-14B.json --dir ./NousCoder-14B $ python3 fw.py verify ./NousCoder-14B ./NousResearch__NousCoder-14B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download NousResearch/NousCoder-14B --revision bea270969fc7edea385a15a492ebeec5cbc6d6a8 --local-dir ./NousCoder-14B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("NousResearch/NousCoder-14B", revision="bea270969fc7edea385a15a492ebeec5cbc6d6a8") model = AutoModelForCausalLM.from_pretrained("NousResearch/NousCoder-14B", revision="bea270969fc7edea385a15a492ebeec5cbc6d6a8", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve NousResearch/NousCoder-14B --revision bea270969fc7edea385a15a492ebeec5cbc6d6a8
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
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
cd84dcec0554561979278f539f54832c49040ef1ea14b2e732235bcc959209cc
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: NousResearch <huggingface.co/NousResearch>Newsgroups: alt.freeweights.textSubject: NousCoder-14BDate: 2026-11-15Commit: bea2709Signed: 2DC28CC7B26A283B ✓
Upstream
NousResearch/NousCoder-14B
Pinned commit
bea270969fc7edea385a15a492ebeec5cbc6d6a8
Manifest
NousCoder-14B.json · .minisig
Manifest sha256
d9657593991e3a87cecebe06e8b926d36844981f55405fdc043a88e0e8002f05
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:45 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/NousResearch/NousCoder-14B.json $ curl -O https://freeweights.allternit.com/manifests/NousResearch/NousCoder-14B.json.minisig $ minisign -Vm NousCoder-14B.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

Qwen/Qwen3-14B · 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 NousResearch/NousCoder-14B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. NousCoder-14B.json. Provenance. Takedown history: none.
Source
huggingface.co/NousResearch/NousCoder-14B

Variants

1 quantized or adapter build of NousCoder-14B. Each has its own license check and page.

SubjectSizeParamsLicenseDate
NousResearch_NousCoder-14B-GGUFHosted (signed) From: bartowski in alt.freeweights.text240 GB—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