CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

a2-rl-e2egit_large-50-32B

Date: 2026-11-15Commit: a343301Signed: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 65.5 GB in all. Published by laion under Apache-2.0.

32.8B params65.5GBa2-rl-e2egit_large-50-32Bsafetensorspermissive
FactsParams32.8BSize65.5 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get laion/a2-rl-e2egit_large-50-32B
# manifest sha256 f2a53d907e85… · 65.5 GB · 40 files
$ fw verify ./a2-rl-e2egit_large-50-32B laion/a2-rl-e2egit_large-50-32B
From sourceHosted (signed)laion/a2-rl-e2egit_large-50-32BLast check: 2026-11-15 04:24 UTC
Fine-tune in StudioRun at homeGet help

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

Fine-tune of Qwen3-32B.

Runs withAIBrixBentoMLCTranslate2ExLlamaV2ExLlamaV3exofastllmFlashInfergpu-unlockKTransformersLitServeLMCacheLMDeployLocalAImistral.rsMLC LLMMooncakeSGLangText Generation WebUItinygradTransformersTriton Inference ServervLLMXinferenceFine-tune withAccelerateAlignment HandbookAxolotlColossal-AIDeepSpeedEasyR1FlashAttentionH2O LLM StudioJAXKerasLiger KernelLitGPTLLaMA-FactoryMegatron-LMms-swiftnanotronOLMo-coreOpenRLHFOumiPEFTPyTorch Lightningsd-scriptsSimpleTunerTorchTitantorchtuneTransformer EngineTRLUnslothverlConvert withAQLMAutoRoundCore ML ToolsExecuTorchGPTQModelLLM CompressormergekitNeural CompressorOliveONNXOptimum QuantoOptimumsafetensorsTensorRT Model OptimizertorchaoEvaluate withAutoevalsDeepEvalEvaluateHELMLightEvallm-evaluation-harnessOpenCompassOpikRagassimple-evalsSWE-benchTruLensWeaveScan withAgentDojoAI Fairness 360DeepTeamDetoxifyFairlearngarakGiskardGuardrailsMCP ScannerModelScanNeMo GuardrailspicklescanpromptfooWorks withAgent Development KitAG2Google AI Edge GalleryAiderany-llmAnythingLLMBAMLbrowser-useCAMELHugging Face Chat UIChatboxCherry StudioClineCodex CLICogneeCrewAIDeerFlowDSPyEnchantedGemini CLIGitHub MCP ServergooseGPT ResearcherGradioGraphitiGuidanceHollamaInstructorKilo CodeLangflowLangGraphLiteLLMLlamaIndexLLMLocalAGILoLLMs WebUIMCP Python SDKMem0MetaGPTNextChatOllama JavaScriptOllama PythonOpenAI Agents SDKopencodeOpenHandsotermOutlinesPage AssistPlaywright MCPPortkey AI GatewayPrivateGPTQwen CodeRWKV RunnerSemantic KernelsmolagentsStrands AgentsVaneXGrammar
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
65.5 GB
Weights
65.5 GB (safetensors)
Parameters
32.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
40, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-32B

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 04:24 UTCpassed

Model card

From the publisher at commit a343301. Shown as plain text with links; images open at the publisher.

a2-rl-e2egit_large — step 50#

RL fine-tune of Qwen3-32B on the e2egit-large task distribution (end-to-end git operations). Training via SkyRL/GRPO on Jupiter (GH200, 16 nodes). Best-reward exported checkpoint.

Training metrics (step 50)#

  • reward/avg_raw_reward: 0.8828
  • reward/avg_pass_at_8: 0.891 (estimated)
  • Peak reward across run: 0.9238 @ step 41

Hyperparameters#

  • Algorithm: RLOO-N (GRPO variant)
  • LR: 9e-6, epochs: 2, max_steps: 60
  • train_batch_size: 64, n_samples_per_prompt: 8
  • max_prompt_length: 32768, strategy: fsdp2
  • Dataset: exp_rpt_e2egit-large

Files

40 files · 65.5 GBWeights 65.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 40 files with their sha256
FileSizesha256
.gitattributes1.75 KBf2ec954b1928743e6f686052af2b57759539e0bcf7579af23c5e700774eb1f52
README.md740 B77584cbd6734e73d33bd9cc8fab24667e4f3d55e5143e95f08326808c9cc8caa
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json2.15 KB5c0a65ba79019eca5a318b5a35325509545834f09b39d8aacbb562bb8ada4cb6
generation_config.json188 B3b101cd89b140b757d0bca469e75570e75789a2423ada90a33ec17707dfacf08
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00014.safetensors4.93 GB2bfa94c413f9dfe8199ecc985fd3c3bf5f06d6a83ee6ea6de818e4f243d2c12f
model-00002-of-00014.safetensors4.88 GB74d7977ebac69fe23783d9fbf09ca856c58dae5bb88b0373451046f6da84cc1b
model-00003-of-00014.safetensors4.88 GB153264f833faa837160121440229fd4ada9ed118d7e8ffd9c8684ab567005703
model-00004-of-00014.safetensors4.88 GB5453ae92de858544f4ae1cd411591148d8f555fe14fe48ef3e9906380fa6ac9a
model-00005-of-00014.safetensors4.88 GB1bfa1bcbc3d29bc1c85b6fc39d044e5e9fa1d88eeac57df9343728e9246f7633
model-00006-of-00014.safetensors4.88 GBdbce6d41a9e554fb66c6cc26bbf49f66379bc920deffa3fbb1b75f2b2991a610
model-00007-of-00014.safetensors4.88 GB9f827426d8355345c0d9f99f4af67607af155514b48785151730ed9b4bbcee4d
model-00008-of-00014.safetensors4.88 GB0b64b4faafc38fe004e7e357682a46a9fb5810769aed58fdaa44aa5d79e63bbb
model-00009-of-00014.safetensors4.88 GB5630830c1dcbe983e3ba610104f6ef6f5c39544d4e399dd912e0454b5176bab6
model-00010-of-00014.safetensors4.88 GBfb9bbfe9692b538721cbb24046cc2f495b9b95923757a56976ea7ff41a0d2086
model-00011-of-00014.safetensors4.88 GB4159dc4138d06cb08643f158f8c6aa7e463f5d9cb16ab4f268da0abdc8d4e8ed
model-00012-of-00014.safetensors4.88 GB836db3b11f84d5efc23835521f45293804ac3c895ff50aaa511b65e6d78662e3
model-00013-of-00014.safetensors4.88 GBa9a3df47408f6c43eab0f662ac7abe0e1c35a6b1a88a605668049f1d1339d1d6
model-00014-of-00014.safetensors2.08 GB36abf252bf7e9799d10134e975523057bd96a5201d3152d4d6b08f4b8121ca1f
model.safetensors.index.json58.4 KB8de55f623820cbf9374d6060adf903efcb7499b958aa4cec3409419ad93d0666
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.43 KB3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5
training_logs/20260501_144658_metrics_a2-rl-e2egit_large_407001.csv8.30 KBa7750096010e5b5924759959ef4f6781f4482627e8372ca168e67550c823469d
training_logs/20260501_144658_metrics_a2-rl-e2egit_large_407002.csv12.4 KB21d24e364b4691723a959ff91eb92af28986b66cc2d3a2c41bfe8d09408f44c1
training_logs/20260501_144658_metrics_a2-rl-e2egit_large_407003.csv1.51 KBe9bbd4f7bb5b19ffa44761a44aebeaaf848b153b81595e9a3a650a16567e9a5d
training_logs/20260501_144658_metrics_a2-rl-e2egit_large_407004.csv1.51 KB26675885ea0726392bef301495951cee20157809a6e6c5fd21606d82abe92983
training_logs/20260501_144658_metrics_report.md18.1 KBda290dffb0ae97f7373a4881f291cffeade6f963eb71b7dd10b280c59e61bdb7
training_logs/20260501_144658_metrics_table.csv22.2 KB2f566eebe7b325764cc326b1e9e0221734dac6fe9d0070a78242741614b9ee05
training_logs/20260501_144658_reward_vs_steps.png128 KBa9447839474bb20754a97786b336006196064c6f319c54f603fc572cff8ee82a
training_logs/20260501_144658_trial_results.csv2.36 MB5bcd6e5a3ec00648206ddb44dc2988e8cd47feac5bbd25e15e008d0e95e71180
training_logs/20260501_144658_turn_count_distribution.png126 KBd74d3d65a1388875dba8d40cfdf833d89e9d6088b99e0a8f3e2ce1e428ba49c0
training_logs/20260501_144658_vllm_metrics_a2-rl-e2egit_large_407002.csv480 KB5134143daf1cd6aec98436b7dc6aa08f3221b94eed53b4b50663b005d4f3edc8
training_logs/20260501_144658_vllm_metrics_a2-rl-e2egit_large_407003.csv26.2 KB05d98bf37acf1f0030b9ad119c391a73efdb6d77186ea9d1f132a4e7808112ca
training_logs/20260501_144658_vllm_metrics_a2-rl-e2egit_large_407004.csv24.9 KB9bfc7325c830e8a7c99f89fcf719dd0f8381ad870b248c649b87c25c58c8383f
training_logs/20260501_144658_vllm_metrics_a2-rl-e2egit_large_407005.csv3.45 KBdeb0edd20d8abfff1e6db6bf9356aa9915a773a7e4ff8bbfda3741e092213a32
training_logs/20260501_144658_vllm_metrics_table.csv715 KB1a9734f79274580411962a10b65d50369253276a34a667fb29f1a6b815bc6c7e
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
a34330132a pinned now2026-11-15 04:24 UTC40 files · 65.5 GB

Use it

$ fw get laion/a2-rl-e2egit_large-50-32B
# manifest sha256 f2a53d907e85… · 65.5 GB · 40 files
$ fw verify ./a2-rl-e2egit_large-50-32B laion/a2-rl-e2egit_large-50-32B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/a2-rl-e2egit_large-50-32B.json --dir ./a2-rl-e2egit_large-50-32B $ python3 fw.py verify ./a2-rl-e2egit_large-50-32B ./laion__a2-rl-e2egit_large-50-32B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/a2-rl-e2egit_large-50-32B --revision a34330132ab1dd0a1c13485b51fdc4c1c6b5003b --local-dir ./a2-rl-e2egit_large-50-32B
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/a2-rl-e2egit_large-50-32B", revision="a34330132ab1dd0a1c13485b51fdc4c1c6b5003b") model = AutoModelForCausalLM.from_pretrained("laion/a2-rl-e2egit_large-50-32B", revision="a34330132ab1dd0a1c13485b51fdc4c1c6b5003b", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/a2-rl-e2egit_large-50-32B --revision a34330132ab1dd0a1c13485b51fdc4c1c6b5003b
Run at homeFine-tune in Studio

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
77584cbd6734e73d33bd9cc8fab24667e4f3d55e5143e95f08326808c9cc8caa
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.textSubject: a2-rl-e2egit_large-50-32BDate: 2026-11-15Commit: a343301Signed: 2DC28CC7B26A283B ✓
Upstream
laion/a2-rl-e2egit_large-50-32B
Pinned commit
a34330132ab1dd0a1c13485b51fdc4c1c6b5003b
Manifest
a2-rl-e2egit_large-50-32B.json · .minisig
Manifest sha256
f2a53d907e85e15ed6eb58a32010007b4429a6d4ccb4d33887b53a1385d4acf3
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/a2-rl-e2egit_large-50-32B.json $ curl -O https://freeweights.allternit.com/manifests/laion/a2-rl-e2egit_large-50-32B.json.minisig $ minisign -Vm a2-rl-e2egit_large-50-32B.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/Qwen3-32B · 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/a2-rl-e2egit_large-50-32B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. a2-rl-e2egit_large-50-32B.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/a2-rl-e2egit_large-50-32B

Related models

All of alt.freeweights.text →
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
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h4_binary_easy-50-8B