WARMIND-1017-FLARE-gb202
WARMIND-1017, prepared as a Flare runtime for four RTX PRO 6000 Blackwell GPUs.
WARMIND-1017 is jcartu's abliterated release of DeepSeek-V4.1-Flash-1017. The refusal direction is inverted in 132 dense tensors and nothing else is touched.
This repository is that model exported to Flare. Flare is the native Rust serving runtime from NVIDIA's spark-local-inference project, led by Luke Alonso of Local Inference Lab. The package uses the same gb202-tp4 layout as Local Inference Lab's own DeepSeek-V4.1-Flash-1017-FLARE gb202 package, and it targets the Flare image Local Inference Lab publishes.
This revision is built on Flare 972e28e4 and FlashInfer 6aaa9b47, the same commits as Local Inference Lab's gb202 revision 6d51b296 (November 7), with the clustered PCIe all-reduce ladder. Download it and run it; there is no hour-plus export to do yourself. This gb202 / main revision ships WARMIND-1017 v1.1 (orth4c), which keeps 0/100 refusals while closing two-thirds of the SQuAD 2.0 unanswerable hallucination gap and matching stock under a grounding system prompt. Other builds stay available: gb202-v1.0-972e28e (original v1.0 a3.0 weights on Flare 972e28e4), gb202-78b18b1 (Flare 78b18b1c) and gb202-6fa01a4 (Flare cc696a6b, for the older release-6fa01a4-main-20261101 image).
At a glance
| Weights | jcartu/WARMIND-1017 @ a6382f22 (v1.1 / orth4c, abstention-preserving edit). Original v1.0 stays on gb202-v1.0-972e28e |
| Base model | deepseek-ai/DeepSeek-V4.1-Flash-1017 (DeepSeek, MIT) |
| Format | Flare runtime package, gb202-tp4 deployment: weights, compiled CUDA kernels and captured execution graphs. Native expert scales (not CSF), runtime-tuned collectives with the gb202_pcie_tp4_clustered_full ladder |
| Hardware | Four 96 GB SM120 GPUs (RTX PRO 6000 Blackwell), tensor parallel 4, Linux x86-64 |
| Runtime | Flare image ghcr.io/local-inference-lab/flare:release-972e28e-main-20261107 (the release and latest tags pointed to it on November 7). Tested on that image; we have not run this package on release-18b16e1-main-20261104. Transformers, vLLM, SGLang and llama.cpp cannot load this format |
| Needs | NVIDIA Container Toolkit (tested with driver 615.78.08), 524 GB (488 GiB) of local NVMe (hf writes straight into the folder), and host RAM for the Engram row cache you choose (32 GiB in the command below), the 5.7 GiB of resident Engram scales, and a few GiB for Flare itself |
| Capacity | 32 concurrent requests, 1,048,576-token context per request, 16,864,512 KV tokens on our box |
| Speculation | Seven MTP draft tokens per round, adaptive verification |
| Engram | 188.8 GiB of tables. Kept on disk by default; RAM optional |
| Size | 524 GB (488 GiB) |
| Signed by | Local development key, namespace local-development, fingerprint fa77427544ec0959c79734f8fb5632e2c1ac97c674ada5e07d6ba127b550ce68 (development-publisher.json) |
| License | MIT for the weights; Apache-2.0 and BSD-3-Clause for the compiled runtime components. See License |
| Access | Public download; no access request needed |
How it differs from LiL's gb202 package
LiL's gb202 revision 6d51b296 (November 7, 11:06 UTC) is built on the same Flare and FlashInfer commits, with native expert scales and runtime-tuned clustered collectives, like this one.
- Weights. WARMIND-1017 instead of stock DeepSeek-V4.1-Flash-1017. The files for the untouched layers and the Engram tables come out byte-identical to LiL's (see License). The edited layers 4 to 36 differ.
- Export settings. joninco's settings: NVFP4 draft head, FP8 Markov head and vocabulary-parallel sampling, with BF16 MLA compute.
- KV capacity. On our box this package holds 16,864,512 KV tokens. LiL's card for
gb202revision6d51b296gives about 16.9 million on four 96 GB GPUs; we have not measured that revision here. - Sampling. Like every DeepSeek V4.1 Flare package, temperature, top-k, min-p and the presence and frequency penalties are fixed at their defaults. A request that sets them is served at the default, not rejected.
- top-p is fixed at 1.0 as well. Vocabulary-parallel sampling does not support a lower top-p. Flare at this commit (since #208) declares no top-p range for DeepSeek V4.1, so a request with a lower top-p is served at 1.0 instead of failing; LiL's
6d51b296is built the same way. - Repetition penalty can be set from 1.0 to 1.1, as in LiL's
6d51b296.
- top-p is fixed at 1.0 as well. Vocabulary-parallel sampling does not support a lower top-p. Flare at this commit (since #208) declares no top-p range for DeepSeek V4.1, so a request with a lower top-p is served at 1.0 instead of failing; LiL's
- Signing. Signed with our own development key, not Local Inference Lab's. Flare asks you to trust it once (see below).
What changed in v1.1 (orth4c, 2026-11-16)
- Abstention-preserving weights (
jcartu/WARMIND-1017@a6382f22). Same Flare972e28e4+ FlashInfer6aaa9b47toolchain andgb202_pcie_tp4_clustered_fullcollective ladder as v1.0 (gb202-v1.0-972e28e), re-exported from the v1.1orth4ccheckpoint. Before applying grimjim's norm-preserving biprojection across layers 4β36, a 4D orthonormal epistemic-abstention basis ([sq_chat, sq_think, gen_epistemic, PC1], extracted from disjoint SQuAD 2.0train-v2.0matched passage pairs + missing-evidence pairs) is projected out of the refusal direction with projection-compensated $\alpha_L = \min(3.5,, 3.0/(1 - |U_4^\top \hat{r}_L|_2^2))$. - Quality gates. Refusals stay at 0/100 true refusals on native (
0/100keyword) and 0/100 true refusals on CSF (1/100keyword). Plain SQuAD 2.0 unanswerable fabrications drop from 37.4% (v1.0) to 28.4% (β9.0 pts, 95% CI β12.0 to β6.0; stock 23.8%); with the strict grounding system prompt, v1.1 scores 25.6% vs stock 24.0% (+1.6 pts, 95% CI β0.2 to +3.6, indistinguishable from stock). 29.4% invented on held-out Round-1 SQuAD2 (vs 35.8% v1.0, 25.0% stock); TruthfulQA MC1 improves from 82.5% to 84.7%. - Multimodal / vision check (POPE MSCOCO val2014, 9,000 items). Measured on the CSF v1.1 package (
enable_thinking: false, C=4): 88.17% overall accuracy (88.08% F1;91.43%random,87.20%popular,85.87%adversarial;49.28%yes-ratio;0/9,000errors or truncations), plus81.67%on a 300-itemenable_thinking: truecheck. - Runtime tip (Flare main >=
6b68b9b4). Tested on bothrelease-972e28e-main-20261107(--stage-only) and upstream Flare6b68b9b4(which merges prefix-cache fixes #298, #302 and snapshot-planning fix #309): on 4x RTX PRO 6000 with RAM Engrams, the CSF v1.1 build ran ~250k-token cold prefill at 19,153 tok/s and context-0llm_decode_benchat C1 320, C8 1,196, C32 2,337 tok/s.
Earlier v1.0 packaging history (78b18b1c -> 972e28e4)
The historical notes below (and the v1.0 baseline speed rows in Measured / How it was built) were recorded on the v1.0 (gb202-v1.0-972e28e) package before the v1.1 132-tensor weight update.
The build exported at Flare 78b18b1c (gb202-tp4-202611042329, on the gb202-78b18b1 branch) used FlashInfer e977747a. This one was exported at Flare 972e28e4 with FlashInfer 6aaa9b47, the commits LiL's gb202 revision 6d51b296 was prepared from, with the same export settings and collective ladder.
Attention masking. FlashInfer
6aaa9b47masks KV storage a request must not read in the attention kernels (1f8ed8a3, Luke Alonso; #73 and #74, Mark Yong), so stale page bytes cannot reach the attention output. This addresses the failure in #116, where requests resuming from the prefix cache under KV pressure ended withprepared model reported device error 6; it was reproduced and the fix validated on Qwen3.8-27B. One report in that issue of the same error with DeepSeek V4.1 on four DGX Sparks (TP4 over RoCE) persisted with the masked kernels and is still open. Kernels are captured at export, so packages exported before these commits keep the old kernels even on a newer image. We have not seen this error on our box with any WARMIND build.top-p handled upstream. The
78b18b1cbuild applied PR #180 locally. Flare at972e28e4carries #208, which declares no DeepSeek top-p range (the same effect as PR #180), so this build is exported from an unmodified Flare commit.MoE autotuning. FlashInfer #78 (Martin Vit) adds whole-batch expert reuse to the cases MoE autotuning measures.
Weights. Unchanged. 170 of the 186 package files, 521.0 GB, are byte-identical to the
78b18b1cbuild, including every weight file. Only the per-rank deployment files (kernels, graphs and initial state, plus one newinitial-state-globalsfile, for rank 3), the manifest andexport.jsonare new.Speed. Both builds' release checks ran on their downloaded copies with the same command, except for the image (
release-18b16e1-main-20261104for the78b18b1cbuild), on different nights:78b18b1cbuildThis build Festr's single-user test 544 tok/s 527 tok/s llm_decode_benchC1299 297 C8 1,144 1,090 C16 1,593 1,604 C32 2,071 2,113 KV capacity 16,807,936 16,864,512 C8 came out 5% lower and the other cells within 3%. We have no same-night A/B of the two native builds, so we cannot separate that from night-to-night spread.
Image. Tested on
release-972e28e-main-20261107.
Other hardware
- DGX Spark (GB10): nero (JMNI-Labs) built WARMIND for GB10 at JMNI-Labs/DeepSeek-V4.1-Flash-1017-abliterated-FLARE. He reports about 6k tok/s prefill on GB10 TP4 and speed close to stock. That build and its numbers are his; we have not tested it ourselves.
Download and run
Download the package with the Hugging Face hf CLI, check it, then serve it with the Flare image:
mkdir -p models flare-state
hf download jcartu/WARMIND-1017-FLARE-gb202 --revision gb202 --local-dir ./models
(cd models && sha256sum -c SHA256SUMS)
echo "flare:x:$(id -u):$(id -g)::/state:/sbin/nologin" > flare-state/passwd
docker run --rm -it --user "$(id -u):$(id -g)" -w /state \
-v "$PWD/flare-state/passwd:/etc/passwd:ro" \
--gpus '"device=0,1,2,3"' -e CUDA_DEVICE_ORDER=PCI_BUS_ID \
--ipc=host --ulimit memlock=-1:-1 --ulimit nofile=1048576:1048576 \
--security-opt seccomp=unconfined -p 127.0.0.1:8000:8000 \
-v "$PWD/models:/models:ro" -v "$PWD/flare-state:/state" \
ghcr.io/local-inference-lab/flare:release-972e28e-main-20261107 \
run /models/model.safetensors \
--publisher-keys /models/development-publisher.json \
--trust-store /state/trust.toml --gpus 0,1,2,3 \
--max-concurrency 32 --mtp-draft-tokens 7 --mtp-adaptive-verification \
--mtp-adaptive-verification-alpha 1 --scheduler-policy throughput \
--embedding-table-storage disk --embedding-table-cache-size 32GiB \
--embedding-table-resident-scales --kv-cache-limit memory \
--host 0.0.0.0 --port 8000
- Download. On our connection the full download took 15 minutes. The checksum step reads all 524 GB again; skip it if you trust the download.
- Other builds. For the build exported at Flare
78b18b1c, download with--revision gb202-78b18b1. Forrelease-6fa01a4-main-20261101, download with--revision gb202-6fa01a4and use that image in the command. Each branch's card has its own numbers. - Trust prompt. On first start Flare shows this package's signing key and asks you to type
local-development.- What it trusts: this one key, not development keys in general. The choice is remembered in
flare-state/trust.toml. - License line: the prompt shows
License: mit, which refers to the DeepSeek weights. - Unattended starts: add
--dangerously-approve-key fa77427544ec0959c79734f8fb5632e2c1ac97c674ada5e07d6ba127b550ce68 --dangerously-accept-publisher local-development, which accepts exactly this key.
- What it trusts: this one key, not development keys in general. The choice is remembered in
- The
passwdline and-w /state. The release image only knows its ownflareuser. When Docker runs as your user ID, Flare cannot find a home directory and stops withcannot resolve home directory, or withPermission deniedfrom the image's working folder. These two lines give your user a home inflare-state. Local Inference Lab's own package hits the same error on this image when run that way. --publisher-keyspoints Flare at this package's public key. Without it Flare stops withpackage signer is not a configured publisher.- Other flags.
--ipc=hostandseccomp=unconfinedare what we ran with. The latter lets Flare useio_uringfor disk-backed Engram inside Docker.--embedding-table-resident-scalesand--kv-cache-limit memoryare Flare's defaults, spelled out.
- Engram in RAM. With about 256 GiB of host RAM, replace the three
--embedding-table-*flags with--embedding-table-storage ram. - Model name.
/v1/modelsreports the export folder name,DeepSeek-V4.1-Flash-1017-warmind-orth4c, as the model's root. Requests useDeepSeek-V4.1-Flash. - Downloading through Flare. Flare can fetch from the Hub itself (
run jcartu/WARMIND-1017-FLARE-gb202 --revision gb202 --filename model.safetensors), but we did not take that path to the end. Usehf download.- Speed: in a 3-minute trial it ran at about 15 MB/s here.
- Key: it would still need
--publisher-keyspointing at the downloadeddevelopment-publisher.json. - Warning: it will warn that the package names
local-developmentrather than this repository as its source.
Send a request
The OpenAI-compatible API serves the model as DeepSeek-V4.1-Flash:
curl --fail http://127.0.0.1:8000/v1/chat/completions \
-H 'Content-Type: application/json' \
-d '{"model":"DeepSeek-V4.1-Flash","messages":[{"role":"user","content":"Explain how a hash table works."}],"max_tokens":1024}'
- Sampling. Defaults are temperature 1.0, top-p 1.0, top-k off, min-p 0, repetition penalty 1.0, and presence and frequency penalties 0. Only
repetition_penalty(1.0 to 1.1) andseedare request-controlled; any other sampling value you send is clamped to its default. - Thinking. Turn it on or off with
"chat_template_kwargs": {"enable_thinking": true}. - Images. The export includes the vision path (
--image-concurrency 4, four image-bearing requests at a time, likegb202), and/v1/modelslists image input. Tested on the CSF v1.1 sibling package (WARMIND-1017-FLARE-CSF-gb202, identical vision tower and edited text layers) across all 9,000 items of POPE MSCOCO val2014 (enable_thinking: false): 88.17 % accuracy (88.08 % F1,91.43/87.20/85.87 %,49.28 %yes-ratio,0/9,000errors), vs81.67 %withenable_thinking: true(300 items).
Tips from running it
- Put the Engram files on XFS or ext4, not btrfs. btrfs routes these small direct reads through extra kernel threads. With the same package copied to both filesystems and the same flags (measured on our sibling export of these weights), a fresh 106k-token prompt took about 10.5 s from btrfs RAID0 (two PCIe 5.0 drives) and about 8 s from XFS on a single PCIe 4.0 drive.
- Engram read-ahead (unmerged). randomvariable's (Naadir Jeewa) Flare branch
topic/engramcache@c2606aaereads 512-byte Engram rows instead of 4 KiB blocks and prefetches the rows the next step will need. It changes the serving binary, not the package. On our box, serving our CSF export of these weights at Flare78b18b1cfrom XFS, a cold 250k-token random-word prompt took 13.6 s with the branch's binary and 22.3 s with therelease-18b16e1-main-20261104binary (two runs each); decode throughput was unchanged. The branch is unmerged and not in any Flare release; we ran only the arithmetic, tool-call and thinking checks on it. - A bigger row cache helps text the model has seen before. We run
--embedding-table-cache-size 64GiBin production. It does not speed up the first read of brand-new text. - Adaptive-verification alpha 1. LiL's card uses
--mtp-adaptive-verification-alpha 0.6. On our box (no PCIe switch, each GPU on its own host bridge), 0.6 was about 5% slower than 1 at 16 concurrent requests (1,425 vs 1,510 tok/s, measured with our November 2 export of these weights on the same image), so the command above uses 1. Try both on switched systems. - Throughput scheduler for concurrent work. It is the right choice for agent swarms and parallel requests. Keep
--max-concurrency 32unless you need memory back.
Measured
Every number below was measured on the files downloaded from this repository and served with the command above (unattended trust flags, a different host port), on release-972e28e-main-20261107 (downloaded from the staging branch that became gb202). Rig: 4x RTX PRO 6000 Blackwell Workstation Edition, Xeon w9-3495X.
| Functional API checks (arithmetic chat, strict JSON schema, 32 tool-call round trips at 4-way concurrency; thinking on) | 34/34 correct |
Requests with top_p 0.95 |
All returned 200 (3 at C1, 8 at C8, 1 streamed) |
| Single-user coding decode (Festr's test, 25 runs) | 527 tok/s (501β549 across runs) |
llm_decode_bench, 30 s cells, context 0 |
C1 297, C8 1,090, C16 1,604, C32 2,113 tok/s |
| KV capacity | 16,864,512 tokens |
| Our 100-prompt refusal battery (keyword screen / true refusals, thinking off, 512 tokens) | 0/100 (0 true) |
| SQuAD 2.0 unanswerable invented answers (Round 2, 500 unanswerable, plain / strict prompt) | 28.4% (+4.6 vs stock, β9.0 vs v1.0) / 25.6% (+1.6 vs stock, CI -0.2 to +3.6) |
| TruthfulQA MC1 (790 items) | 84.7% (+2.2 pts vs v1.0; stock 87.1%) |
The quality and refusal evaluations of the WARMIND edit itself are in EVALUATION-1017.md: MMLU within noise of stock, a KL diagnostic, and blind-labelled refusals. They were run on the vLLM CSF container, jcartu/DeepSeek-V4.1-Flash-1017-abliterated-lossless-CSF, whose 132 edited tensors are byte-identical to the ones exported here.
How it was built
Source. The 82 weight and runtime files of
jcartu/WARMIND-1017were hashed and matched against that repository'sSHA256SUMS.Export. Flare's Ignition exported the package at Flare commit
972e28e4(November 5), the commit behind therelease-972e28e-main-20261107image and the one LiL'sgb202revision6d51b296was prepared from. No pull requests were applied.- #154 by Brandon M. Music, which lets a 32-request export fit in 96 GB of VRAM, and #208, the top-p fix, are merged at this commit.
- FlashInfer
6aaa9b47is the revision LiL'sgb202revision6d51b296was prepared with. Flare's own pin at this commit,1f8ed8a3, is five commits earlier; the five later commits are the paged-attention masks (#73, #74), RoCE and io_uring changes (#75, #76) and the MoE autotuning cases (#78).
The full command, commits and settings are in
export.json. Autotuning ran at Ignition's default effort.ignition export <WARMIND-1017> --gpus 0,1,2,3 \ --max-concurrency 32 --prefill-chunk-size 4096 --image-concurrency 4 \ --mtp-draft-tokens 7 --speculative-token-capacity 128 --speculative-graph-budget 64 \ --mla-compute-mode bf16 --draft-head-quantization nvfp4 --markov-head-quantization fp8 \ --vocabulary-parallel-sampling --expert-scale-compression native \ --collective-tuning runtime \ --collective-ladder ignition/preparation/ladders/gb202_pcie_tp4_clustered_full.json \ --compile-workers 8Pre-upload checks. Before upload, the package was served back to back with our production build at the time (our CSF export at Flare
78b18b1c), with the same flags, using local builds of Flare with the Engram read-ahead branch above (c2606aae, andc2606aaemerged onto972e28e4for this package). It passed the harness's arithmetic (sent with top_p 0.95), tool-call and thinking checks. It ran at 307, 1,128, 1,642 and 2,183 tok/s at C1, C8, C16 and C32, against 306, 1,199, 1,628 and 2,258 for the production CSF build, and held 16,835,456 KV tokens. Cold-prefill times from that run are not reported here, because this package was read from Btrfs and the production package from XFS.Release checks. After upload, it was downloaded back from this repository with the command above, and every package file was matched against
SHA256SUMS. The Measured numbers were taken on that download.
Files
| File | What it is |
|---|---|
model.safetensors |
Package manifest and signature. Point Flare at this file. The Hub's parameter count describes this manifest, not the model |
deployments/gb202-tp4/ |
Compiled kernels, captured graphs and initial state for each of the four ranks |
weights/ |
Model weights per rank, plus the Engram tables and their scales |
development-publisher.json |
Public key that verifies the package signature |
export.json |
Exact export command, Flare commits, source revision and signer |
SHA256SUMS |
SHA-256 of every file in the repository except itself and the Hub's .gitattributes |
LICENSE, LICENSES/, NOTICE |
License texts and notices |
Keep the files together under their original names.
Lineage and credits
- Base weights: DeepSeek-AI,
deepseek-ai/DeepSeek-V4.1-Flash-1017@1bae0e1088993b9b82de08f59de5be5a34e42170, MIT. - Method: grimjim, Norm-Preserving Biprojected Abliteration.
- Refusal directions and the original s3.0 recipe:
distributedcognition/DeepSeek-V4.1-Flash-abliterated(norm-preserving biprojection, scale 3.0, layers 4 to 36), built on the previous DeepSeek-V4.1-Flash. - WARMIND-1017: operator re-implementation, validation, 1017 re-abliteration and evaluation by jcartu (WARMIND-1017).
- Flare: the runtime and the export toolchain, by NVIDIA and the Flare community contributors, led by Luke Alonso of Local Inference Lab.
- Local Inference Lab: the
gb202runtime layout and the release image this package targets, from Luke Alonso and Festr. Their official DeepSeek-V4.1-Flash-1017-FLARE package is the reference this one follows. - Martin Vit (
voipmonitor): the clustered PCIe all-reduce collectives and ladders this build is tuned with (Flare #174, FlashInfer #70) and the shared startup tuning storage (Flare #197, FlashInfer #72) that gives it back its KV capacity. He also wrote FlashInfer #78 (MoE autotuning). - Mark Yong: the attention masking fixes in FlashInfer #73 and #74 and the fused-MoE fix in #71.
- Luke Alonso: the attention operand masking in FlashInfer
1f8ed8a3. - Jason Cook (
original-el8): the DeepSeek V4.1 top-p fix in Flare #208. - joninco: the export settings that bring a self-exported package to
gb202speed. - Brandon M. Music: the export memory fix in #154.
- FlashInfer and the b12x authors: the kernels Flare compiles into this package (FlashInfer
6aaa9b47). - This package: export, qualification and these documents by jcartu on a 4x RTX PRO 6000 build machine. Packaging review by Claude Fable.
- nero (JMNI-Labs): the DGX Spark (GB10) build of WARMIND (updated to v1.1).
- pangfather, rascazzione, el8, ufear: community evaluation and discussion motivating the v1.1 epistemic-abstention subspace separation.
License
- Weights. The DeepSeek-V4.1-Flash-1017 weights are under the MIT License (LICENSE, Copyright (c) 2023 DeepSeek). The WARMIND edit adds no terms.
- Compiled runtime components. The package's compiled CUDA kernels and captured graphs were produced by Flare, under the Apache License 2.0 (LICENSES/Flare-Apache-2.0.txt, Copyright NVIDIA CORPORATION & AFFILIATES and Flare community contributors).
- FlashInfer/b12x kernels are included, also Apache 2.0 (LICENSES/FlashInfer-Apache-2.0.txt).
- CUTLASS and FlashAttention-3 components bundled with FlashInfer are under the BSD-3-Clause license (LICENSES/CUTLASS-BSD-3-Clause.txt, LICENSES/FlashAttention3-BSD-3-Clause.txt).
- See NOTICE for the full attribution.
- Local Inference Lab. No Local Inference Lab license applies here. This is not a Local Inference Lab release, and nothing from LiL's CSF containers is in it.
- What is shared: 36 of the package's weight files are byte-identical to files in LiL's MIT-licensed
gb202package (revisionscefb84d2,e659bf6c,b3c7e7c6,32385269and6d51b296): the four Engram files and, for each rank, the weight files for the untouched layers 0β3 and 37β39 plusmisc, 274.6 GB in all. (LICENSEis DeepSeek's MIT text in both repositories.) - Why: Ignition serializes the same DeepSeek bytes the same way, and its content-addressed cache reused files it already held after this export had verified its own source bytes.
- What is new: the 132 rank files for layers 4β36 are the WARMIND edit (unchanged from the
78b18b1cbuild). The kernels, the graphs and the manifest were produced by this export. - Check it yourself: compare the weight files' SHA-256s on the Hub. The weight files that differ are exactly the WARMIND edit; the kernels, graphs and manifest differ because they are this export's.
- What is shared: 36 of the package's weight files are byte-identical to files in LiL's MIT-licensed
Model tree for jcartu/WARMIND-1017-FLARE-gb202
Base model
deepseek-ai/DeepSeek-V4.1-Flash-1017