CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
From: bartowski <huggingface.co/bartowski>Newsgroups: alt.freeweights.textSubject:

baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF

Date: 2026-11-15Commit: 74454b2Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 353 GB in all. Published by bartowski under Apache-2.0.

text353GBbaidu_ERNIE-4.5-21B-A3B-Thinking-GGUFggufpermissive
FactsParamsnot statedSize353 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
# manifest sha256 3758c0095c8a… · 353 GB · 30 files
$ fw verify ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
From sourceHosted (signed)bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUFLast check: 2026-11-15 05:01 UTC
Run at homeGet help

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

Quantized of ERNIE-4.5-21B-A3B-Thinking.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
353 GB
Weights
48.5 MB (smallest of 28 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
Apache-2.0 (permissive)
Files
30, each with a sha256
Publisher
bartowski
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: baidu/ERNIE-4.5-21B-A3B-Thinking

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 05:01 UTCpassed

Model card

From the publisher at commit 74454b2. Shown as plain text with links; images open at the publisher.

Llamacpp imatrix Quantizations of ERNIE-4.5-21B-A3B-Thinking by baidu#

Using llama.cpp release b6443 for quantization.

Original model: https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking

All quants made using imatrix option with dataset from here combined with a subset of combined_all_small.parquet from Ed Addario here

Run them in LM Studio

Run them directly with llama.cpp, or any other llama.cpp based project

Prompt format#

No prompt format found, check original model page

Download a file (not the whole branch) from below:#

FilenameQuant typeFile SizeSplitDescription
ERNIE-4.5-21B-A3B-Thinking-bf16.ggufbf1643.66GBfalseFull BF16 weights.
ERNIE-4.5-21B-A3B-Thinking-Q8_0.ggufQ8_023.21GBfalseExtremely high quality, generally unneeded but max available quant.
ERNIE-4.5-21B-A3B-Thinking-Q6_K_L.ggufQ6_K_L18.15GBfalseUses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q6_K.ggufQ6_K18.08GBfalseVery high quality, near perfect, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q5_K_L.ggufQ5_K_L15.82GBfalseUses Q8_0 for embed and output weights. High quality, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q5_K_M.ggufQ5_K_M15.75GBfalseHigh quality, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q5_K_S.ggufQ5_K_S15.23GBfalseHigh quality, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q4_1.ggufQ4_113.88GBfalseLegacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
ERNIE-4.5-21B-A3B-Thinking-Q4_K_L.ggufQ4_K_L13.56GBfalseUses Q8_0 for embed and output weights. Good quality, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q4_K_M.ggufQ4_K_M13.50GBfalseGood quality, default size for most use cases, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q4_K_S.ggufQ4_K_S13.01GBfalseSlightly lower quality with more space savings, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q4_0.ggufQ4_012.78GBfalseLegacy format, offers online repacking for ARM and AVX CPU inference.
ERNIE-4.5-21B-A3B-Thinking-IQ4_NL.ggufIQ4_NL12.60GBfalseSimilar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
ERNIE-4.5-21B-A3B-Thinking-IQ4_XS.ggufIQ4_XS11.96GBfalseDecent quality, smaller than Q4_K_S with similar performance, recommended.
ERNIE-4.5-21B-A3B-Thinking-Q3_K_XL.ggufQ3_K_XL10.73GBfalseUses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
ERNIE-4.5-21B-A3B-Thinking-Q3_K_L.ggufQ3_K_L10.66GBfalseLower quality but usable, good for low RAM availability.
ERNIE-4.5-21B-A3B-Thinking-Q3_K_M.ggufQ3_K_M10.30GBfalseLow quality.
ERNIE-4.5-21B-A3B-Thinking-IQ3_M.ggufIQ3_M10.29GBfalseMedium-low quality, new method with decent performance comparable to Q3_K_M.
ERNIE-4.5-21B-A3B-Thinking-Q3_K_S.ggufQ3_K_S9.85GBfalseLow quality, not recommended.
ERNIE-4.5-21B-A3B-Thinking-IQ3_XS.ggufIQ3_XS9.35GBfalseLower quality, new method with decent performance, slightly better than Q3_K_S.
ERNIE-4.5-21B-A3B-Thinking-IQ3_XXS.ggufIQ3_XXS8.99GBfalseLower quality, new method with decent performance, comparable to Q3 quants.
ERNIE-4.5-21B-A3B-Thinking-Q2_K_L.ggufQ2_K_L8.16GBfalseUses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
ERNIE-4.5-21B-A3B-Thinking-Q2_K.ggufQ2_K8.09GBfalseVery low quality but surprisingly usable.
ERNIE-4.5-21B-A3B-Thinking-IQ2_M.ggufIQ2_M7.16GBfalseRelatively low quality, uses SOTA techniques to be surprisingly usable.
ERNIE-4.5-21B-A3B-Thinking-IQ2_S.ggufIQ2_S6.37GBfalseLow quality, uses SOTA techniques to be usable.
ERNIE-4.5-21B-A3B-Thinking-IQ2_XS.ggufIQ2_XS6.35GBfalseLow quality, uses SOTA techniques to be usable.
ERNIE-4.5-21B-A3B-Thinking-IQ2_XXS.ggufIQ2_XXS5.57GBfalseVery low quality, uses SOTA techniques to be usable.

Embed/output weights#

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli#

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF --include "baidu_ERNIE-4.5-21B-A3B-Thinking-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF --include "baidu_ERNIE-4.5-21B-A3B-Thinking-Q8_0/*" --local-dir ./

You can either specify a new local-dir (baidu_ERNIE-4.5-21B-A3B-Thinking-Q8_0) or download them all in place (./)

ARM/AVX information#

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Click to view Q4_0_X_X information (deprecated

I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.

Click to view benchmarks on an AVX2 system (EPYC7702)

modelsizeparamsbackendthreadstestt/s% (vs Q4_0)
qwen2 3B Q4_01.70 GiB3.09 BCPU64pp512204.03 ± 1.03100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64pp1024282.92 ± 0.19100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64pp2048259.49 ± 0.44100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64tg12839.12 ± 0.27100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64tg25639.31 ± 0.69100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64tg51240.52 ± 0.03100%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64pp512301.02 ± 1.74147%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64pp1024287.23 ± 0.20101%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64pp2048262.77 ± 1.81101%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64tg12818.80 ± 0.9948%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64tg25624.46 ± 3.0483%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64tg51236.32 ± 3.5990%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64pp512271.71 ± 3.53133%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64pp1024279.86 ± 45.63100%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64pp2048320.77 ± 5.00124%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64tg12843.51 ± 0.05111%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64tg25643.35 ± 0.09110%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64tg51242.60 ± 0.31105%

Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation

Which file should I choose?#

Click here for details

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits#

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Files

30 files · 353 GBWeights 48.5 MB (smallest of 28 GGUF variants). Sizes and sha256 from the signed manifest.
Show all 30 files with their sha256
FileSizesha256
.gitattributes3.78 KB0e02f8339126d197b64e6240c91002b109a7915bc5f8c2f9118af68b05da55f9
README.md15.2 KB07c3a090102b42043275dadb1d9f5f0828c6a52afc8b5bbf97b8a349cb1a6546
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ2_M.gguf7.16 GB694dc2b08354cc9e2eb3a605a39694cad15790a78bf42a88acc89faa056ece5e
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ2_S.gguf6.37 GB45a28033f357aae1e07c909d20672e525903e5f6955c773ef32676f9d8900800
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ2_XS.gguf6.35 GBf07daec0f4debde1eb78241ace8538945c979d63415a078094d2c1daf4525bab
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ2_XXS.gguf5.57 GB387a0b5d69e5d4bf7c7645c4a063383b7a79635413600132de2cabf61cece586
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ3_M.gguf10.3 GBc07db8869da045ac4989592f388e6d6f8605e2dcc5a1d8515ca9c870f7f11005
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ3_XS.gguf9.35 GB35142705c2b1e67ec068c07ad165f44f5c784bb21b7e74784b1c740dad8ea86e
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ3_XXS.gguf8.99 GB42ec0efdeb1534be0bfc148593e840705d90ffde02e6151dfca5f64e2f403900
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ4_NL.gguf12.6 GBbac142b542e06b1f340a1967b2c266f6676ce0bec6b03bb03d6b293089eec675
baidu_ERNIE-4.5-21B-A3B-Thinking-IQ4_XS.gguf12.0 GB75263c4d84eac6f9d840a9a6fd048bd3eb1f42e738d73500f09c4f107f5d93f2
baidu_ERNIE-4.5-21B-A3B-Thinking-Q2_K.gguf8.09 GB20e71dbb028e78b315250315f64a531c3031ec72c08f7a9fafc3e629deb947eb
baidu_ERNIE-4.5-21B-A3B-Thinking-Q2_K_L.gguf8.16 GBf9c0e71ff6db4e612c0073d891a16c2b927f0dd2add6062663e21642dcd3c533
baidu_ERNIE-4.5-21B-A3B-Thinking-Q3_K_L.gguf10.7 GB6d91a6ac9ae9ecb9ff02e6470452eab411c1cfc4a77611e4d5750a63ad4f6b1e
baidu_ERNIE-4.5-21B-A3B-Thinking-Q3_K_M.gguf10.3 GBabcc73c027a5396c960cc9ef230898f74504274084de4e85b28c37c8cabfba6a
baidu_ERNIE-4.5-21B-A3B-Thinking-Q3_K_S.gguf9.85 GB92be5a64ae6d85cebbb78a96791c0e60439d3d69afd88b1b7ea078ef4bd9b23e
baidu_ERNIE-4.5-21B-A3B-Thinking-Q3_K_XL.gguf10.7 GBf05d43b61300ace42aa5ec96a7f5790b55b41d5c8899b2102d1bedc6a165fdd5
baidu_ERNIE-4.5-21B-A3B-Thinking-Q4_0.gguf12.8 GB9d8dc8340451540bf9f71485a4e04472876ad2343aea2d46f8758c933ed4fab0
baidu_ERNIE-4.5-21B-A3B-Thinking-Q4_1.gguf13.9 GBd593843b80e5e0845512760cbaf6f54f4ba1330ce63d015daca32e241531e8a2
baidu_ERNIE-4.5-21B-A3B-Thinking-Q4_K_L.gguf13.6 GBf5e7cbf5129d7dad550fd04c37395344ec92629e706deff060f9bccdf1192623
baidu_ERNIE-4.5-21B-A3B-Thinking-Q4_K_M.gguf13.5 GBf309f225c413324c585e74ce28c55e76dec25340156374551d39707fc2966840
baidu_ERNIE-4.5-21B-A3B-Thinking-Q4_K_S.gguf13.0 GB1f718402e688dbc7be2ee2074a1fba96ff8f588159ecccd0420b52199323b3b3
baidu_ERNIE-4.5-21B-A3B-Thinking-Q5_K_L.gguf15.8 GB96bb2a1da80c300c9f38885b39eba102f12bf2a33e6bf9ffb98b38e635e11a5c
baidu_ERNIE-4.5-21B-A3B-Thinking-Q5_K_M.gguf15.8 GB2c256393d856e25f0e28814c90067f05d70af71cc091a59c1b38048b6f589199
baidu_ERNIE-4.5-21B-A3B-Thinking-Q5_K_S.gguf15.2 GBb9e03fa44c61846bbf2bd0b323d86fa6d6c5866de0ee71508986bde1960355d7
baidu_ERNIE-4.5-21B-A3B-Thinking-Q6_K.gguf18.1 GB7957a9f6b968b08bf0f6e31412b873499f88a9e91e53f6d878db08e26e22fd34
baidu_ERNIE-4.5-21B-A3B-Thinking-Q6_K_L.gguf18.1 GBaaed390db69339e04c826cd78858425ea49f8c9fddc434b1c9a78bc86f6b7db7
baidu_ERNIE-4.5-21B-A3B-Thinking-Q8_0.gguf23.2 GB3da291910d471dc89394de7bdf294142cd09088e5b1d822b4be69010794392a0
baidu_ERNIE-4.5-21B-A3B-Thinking-bf16.gguf43.7 GB0f5091f916c19ab9cd09d8045e184e85e6ee0d69f3196d2c6d406e842d17a312
baidu_ERNIE-4.5-21B-A3B-Thinking-imatrix.gguf48.5 MB2f15f47025d23b67c814368b772444ead16ed1a3eceb637886bd661c9e21ef64
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
74454b2e6c pinned now2026-11-15 05:01 UTC30 files · 353 GB

Use it

$ fw get bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
# manifest sha256 3758c0095c8a… · 353 GB · 30 files
$ fw verify ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.json --dir ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF $ python3 fw.py verify ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF ./bartowski__baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF --revision 74454b2e6c542cf84eaf90c1d6e52e126a74e983 --local-dir ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
llama.cppDownload one GGUF variant (baidu_ERNIE-4.5-21B-A3B-Thinking-imatrix, 48.5 MB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF --include "baidu_ERNIE-4.5-21B-A3B-Thinking-imatrix*" --local-dir ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF $ llama-server -m ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF/baidu_ERNIE-4.5-21B-A3B-Thinking-imatrix.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF/baidu_ERNIE-4.5-21B-A3B-Thinking-imatrix.gguf\n' > Modelfile $ ollama create baidu-ernie-4.5-21b-a3b-thinking-gguf -f Modelfile
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model baidu/ERNIE-4.5-21B-A3B-Thinking: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
07c3a090102b42043275dadb1d9f5f0828c6a52afc8b5bbf97b8a349cb1a6546
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: bartowski <huggingface.co/bartowski>Newsgroups: alt.freeweights.textSubject: baidu_ERNIE-4.5-21B-A3B-Thinking-GGUFDate: 2026-11-15Commit: 74454b2Signed: 2DC28CC7B26A283B ✓
Upstream
bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
Pinned commit
74454b2e6c542cf84eaf90c1d6e52e126a74e983
Manifest
baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.json · .minisig
Manifest sha256
3758c0095c8a074e9cff17541eace4de37461049c4824bf1366c73d56288dda3
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:01 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.json.minisig $ minisign -Vm baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.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

baidu/ERNIE-4.5-21B-A3B-Thinking · this model is a quantization of it

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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF

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