CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.kimi / kimi-k2-r2egym_sandboxes-maxeps-32k
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.kimiSubject:

kimi-k2-r2egym_sandboxes-maxeps-32k

Date: 2026-11-15Commit: 257c5b0Signed: 2DC28CC7B26A283B ✓

Text generation model with 0M parameters. Safetensors weights, 16.4 GB in all. Published by laion under Apache-2.0.

0M params16.4GBkimi-k2-r2egym_sandboxes-maxeps-32ksafetensorspermissive
FactsParams0MSize16.4 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get laion/kimi-k2-r2egym_sandboxes-maxeps-32k
# manifest sha256 4cb78e977a63… · 16.4 GB · 23 files
$ fw verify ./kimi-k2-r2egym_sandboxes-maxeps-32k laion/kimi-k2-r2egym_sandboxes-maxeps-32k
From sourceHosted (signed)laion/kimi-k2-r2egym_sandboxes-maxeps-32kLast check: 2026-11-15 04:27 UTC
Run at homeGet help

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

Fine-tune of Qwen3-8B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.4 GB
Weights
16.4 GB (safetensors)
Parameters
0M
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
23, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.kimi
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-8B

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 04:27 UTCpassed

Model card

From the publisher at commit 257c5b0. Shown as plain text with links; images open at the publisher.

kimi-k2-r2egym_sandboxes-maxeps-32k#

This model is a fine-tuned version of Qwen/Qwen3-8B on the penfever/kimi-k2-r2egym_sandboxes-maxeps-32k dataset.

Model description#

More information needed

Intended uses & limitations#

More information needed

Training and evaluation data#

More information needed

Training procedure#

Training hyperparameters#

The following hyperparameters were used during training:

  • learning_rate: 4e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 7.0
Training results#
Framework versions#
  • Transformers 4.56.1
  • Pytorch 2.9.1+cu128
  • Datasets 4.4.1
  • Tokenizers 0.22.1

Files

23 files · 16.4 GBWeights 16.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 23 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.43 KBa748f81d038e108d745ce42c625b4b53e417a5638b53c6d8151a020b56b64468
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
all_results.json544 Bd90c91bacf332a56d919c79277248d58744097d38940dedb395b53c83daaf56c
chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json1.54 KB0990b6c9886d3c687f6a36dfb9bc3d82c2b58092a1cf32ca771fb0fb858256c4
generation_config.json188 B7ba4fb1eb8982970a54c98414d98567d29adf420768362345ff908e190a08bdb
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors4.90 GBb559a7c421221899e57d92a9a72ea3950364182825ccc69c03acb52cc57e3dd8
model-00002-of-00004.safetensors4.92 GB90e9cae4a405e5597f63b36c02c8a0a019364bde30a3eb0a49e7e4592754e95e
model-00003-of-00004.safetensors4.98 GBc842793ca5bdeddfd88b7fc61f8503ab96256d1230df746e6d39d43726795fc6
model-00004-of-00004.safetensors1.58 GB2af1461f2167bd600ede6c804470a7523d7bb5d1b886ce57ef72f2727b8b8142
model.safetensors.index.json32.9 KB9befa4b90440360a9eea244d7c3ab235d0df1e536929078af008d1895522ec7e
run_summary.json487 B6c08117c9aa8d49637528527ec57ef1ca47b8bdfdc7e9163fc0d6ada31d46a4a
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.43 KB776e3ac0537ac47639ddbfd840314938cfb7188be09f7436ed6704efb338ac77
train_results.json544 Bd90c91bacf332a56d919c79277248d58744097d38940dedb395b53c83daaf56c
trainer_log.jsonl51.6 KBb64cb769d56d32fdb328a0b02ed7d4660454752328b5d948bb6c76a70ff3364f
trainer_state.json83.8 KBe2f31f77e8530a4e3acab4ca4b5fe89a3e03e457e0819e983a2efe2fbf12ee31
training_args.bin8.59 KBdf380c0832e95e16f4f549bd8cefbff9add4cefa327f1cd74bbf1218cc50e1fe
training_loss.png42.2 KBd44c27a7de4b11a95cad14db8cbee1a9d3f05493c00436541f409190e496a9fc
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
257c5b05ca pinned now2026-11-15 04:27 UTC23 files · 16.4 GB

Use it

$ fw get laion/kimi-k2-r2egym_sandboxes-maxeps-32k
# manifest sha256 4cb78e977a63… · 16.4 GB · 23 files
$ fw verify ./kimi-k2-r2egym_sandboxes-maxeps-32k laion/kimi-k2-r2egym_sandboxes-maxeps-32k
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/kimi-k2-r2egym_sandboxes-maxeps-32k.json --dir ./kimi-k2-r2egym_sandboxes-maxeps-32k $ python3 fw.py verify ./kimi-k2-r2egym_sandboxes-maxeps-32k ./laion__kimi-k2-r2egym_sandboxes-maxeps-32k.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/kimi-k2-r2egym_sandboxes-maxeps-32k --revision 257c5b05caf1c3362ff720bdc5d076f375342fe0 --local-dir ./kimi-k2-r2egym_sandboxes-maxeps-32k
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("laion/kimi-k2-r2egym_sandboxes-maxeps-32k", revision="257c5b05caf1c3362ff720bdc5d076f375342fe0") model = AutoModelForCausalLM.from_pretrained("laion/kimi-k2-r2egym_sandboxes-maxeps-32k", revision="257c5b05caf1c3362ff720bdc5d076f375342fe0", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/kimi-k2-r2egym_sandboxes-maxeps-32k --revision 257c5b05caf1c3362ff720bdc5d076f375342fe0
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
a748f81d038e108d745ce42c625b4b53e417a5638b53c6d8151a020b56b64468
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: laion <huggingface.co/laion>Newsgroups: alt.freeweights.kimiSubject: kimi-k2-r2egym_sandboxes-maxeps-32kDate: 2026-11-15Commit: 257c5b0Signed: 2DC28CC7B26A283B ✓
Upstream
laion/kimi-k2-r2egym_sandboxes-maxeps-32k
Pinned commit
257c5b05caf1c3362ff720bdc5d076f375342fe0
Manifest
kimi-k2-r2egym_sandboxes-maxeps-32k.json · .minisig
Manifest sha256
4cb78e977a63455afe73312452beaa5698db5a21f6456325b8f971f063695bb9
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:27 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/kimi-k2-r2egym_sandboxes-maxeps-32k.json $ curl -O https://freeweights.allternit.com/manifests/laion/kimi-k2-r2egym_sandboxes-maxeps-32k.json.minisig $ minisign -Vm kimi-k2-r2egym_sandboxes-maxeps-32k.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/Qwen3-8B · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/kimi-k2-r2egym_sandboxes-maxeps-32k
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. kimi-k2-r2egym_sandboxes-maxeps-32k.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/kimi-k2-r2egym_sandboxes-maxeps-32k

Related models

All of alt.freeweights.kimi →
From: laion <huggingface.co/laion>Subject: kimi-k2t-freelancer-32ep-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k
From: mlx-community <huggingface.co/mlx-community>Subject: Kimi-Linear-48B-A3B-Instruct-4bit