Downloads · 30 days
31
5% of all-time downloads
wrldsuksgo2mars/DeepSeek-V4-Pro-0813-EXL3-K2-calibrated-v1
DeepSeek-V4-Pro-0813-EXL3-K2-calibrated-v1 is a text generation model from wrldsuksgo2mars. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
This is a complete, unsliced EXL3 K2 checkpoint of deepseek-ai/DeepSeek-V4-Pro-0813. It carries the original dense/shared weights and K2 trellis encodings for every routed expert in all 61 base layers and all three na…
Downloads · 30 days
31
5% of all-time downloads
All-time downloads
580
Public
Parameters
231B
438 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors438 GB · 100%
How the weights are stored.
I16203B · 88%
From the Hugging Face model README
This is a complete, unsliced EXL3 K2 checkpoint of
deepseek-ai/DeepSeek-V4-Pro-0813.
It carries the original dense/shared weights and K2 trellis encodings for every
routed expert in all 61 base layers and all three native dSpark blocks. The
standard Hugging Face artifact contains 297,238 tensors in 51 shards, with
407.57 GiB of tensor payload. config.json carries only the compact EXL3
format declaration; the full per-tensor storage map is kept separately in
quantize_config.json.
The complete inference engine, five-host launcher, native source, architecture
documentation, reproducible build, and public benchmark record are available
in tpurtell/ds4rt-pro-rtx-4spark.
The supported release topology is one NVIDIA RTX PRO 6000 Blackwell 96 GB
coordinator plus four NVIDIA DGX Spark expert workers on a dedicated 400-Gb/s
path.
For the published v1 coordinator and Spark images, start with the
repository's quick-deploy guide:
git clone --recurse-submodules \
https://github.com/tpurtell/ds4rt-pro-rtx-4spark.git
cd ds4rt-pro-rtx-4spark
# Populate this exact model revision on all five hosts, then configure the
# four Spark host/address pairs in ds4rt.config.
./run.sh --dry-run
./run.sh
The repository also documents the system architecture, source build, and machine-readable Pro v1 measurements.
The encoder replayed a frozen, deterministic 1,426-prompt corpus containing about 1.081 million English-, Chinese-, code-, reasoning-, instruction-, and structured-output-focused tokens through the real learned routers. Naturally under-covered experts were augmented deterministically from router ranks 7–12 to a 1,024-row target, with the declared isotropic recovery residual used only when that natural tail was exhausted. Each dSpark block used a deterministic 327,680-anchor sample of the same activation stream.
The run was streamed layer by layer with bounded two-RTX Hessians, resumable batch capture/replay, per-projection numerical validation, and a retained per-layer/expert error and coverage ledger. No Spark compute was used during quantization.
The final checkpoint passed its complete tensor/shape/digest contract and was
served on the open-source
DS4RT Pro v1 engine: one
RTX PRO 6000 Blackwell coordinator on a 400-Gb/s link plus four DGX Spark TP4
expert ranks, using balanced FP8 KV and adaptive dSpark.
| Post-fix gate | Result |
|---|---|
| Tool Eval Bench 2.3.2, all 69 scenarios, no thinking | 86/100 (118/138 points; 54 pass / 10 partial / 5 fail) |
| Seven-case semantic decode, 35 generations | 38.08 tok/s |
| Code slice of the same decode blend | 52.50 tok/s |
| Low-entropy repeated-word decode, best of five | 68.09 tok/s |
| Fresh source-code 32K prefill, median over two | 1,663.5 tok/s |
| Repeated-prefix retained 32K + 32K prefill, median over two | 2,039.0 tok/s |
| Adaptive dSpark acceptance on the semantic blend | 3,568/5,577 (63.98%) |
These are August 21 post-attention-fix measurements. Earlier Tool Eval figures
on this card were invalidated by the attention defect and have been replaced,
not combined with the corrected run. The 68.09 tok/s result asks for orchid
exactly 100 times; the 2,039.0 tok/s retained result extends a repeated-alpha
prefix and excludes prefix construction. They are explicit low-entropy
ceilings rather than semantic-workload claims.
Tool Eval's safety gate did not pass: it flagged TC-34, TC-42, TC-58, and TC-60. Treat the score as tool-use quality evidence, not a safety qualification. All 69 scenarios completed without an HTTP/backend failure.
The complete nine-cell C1/C2/C4 decode matrix (27 timed runs) and all 63 requests finished without a serving failure. Every timed repeat-decode and prefill sample completed full attention and numeric progression with zero request-time CUDA graph captures.
| 2K prompt + 128 generated tokens | C1 | C2 aggregate | C4 aggregate |
|---|---|---|---|
| 0 context | 37.6 | 49.0 | 54.2 |
| 4K context | 30.2 | 44.6 | 53.8 |
| 8K context | 29.7 | 47.5 | 50.6 |
The full fresh/retained prefill matrix, per-cell measurement contract, and provenance are kept in the linked public benchmark record rather than copied into this weight repository.
The original model card follows for architecture, prompting, benchmark, and license information. Its native-weight vLLM/SGLang launch examples are not EXL3 serving instructions for this checkpoint.
DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.
DeepSeek-V4-Pro-0813 outperforms DeepSeek-V4-Pro (Preview) on the benchmarks listed below, and is broadly competitive with the strongest proprietary models available.
<div align="center">| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) |
|---|---|---|---|---|---|---|---|---|
| HLE (wo / w tools) | 42.7 / 60.0 | 37.8 / 51.5 | 37.7 / 48.2 | 34.8 / 45.1 | 40.5 / 54.7 | 43.5 / 56.0 | 49.8 / 57.9 | 53.3 / 63.0 |
| Terminal Bench 2.1 | 87.9 | 82.7 | 72.1 | 61.8 | 81.0 | 88.3 | 85.0 | 88.0 |
| NL2Repo | 61.5 | 54.2 | 38.5 | 39.4 | 48.9 | - | 69.7 | - |
| Cybergym | 83.3 | 76.7 | 52.7 | 38.7 | - | 80.0 | 78.3 | 83.1 |
| DeepSWE | 62.7 | 54.4 | 12.8 | 7.3 | 46.2 | 67.5 | 58.0 | 70.0 |
| Toolathlon-Verified | 74.1 | 70.3 | 55.9 | 49.7 | 59.9 | 76.5 | 76.2 | 77.9 |
| Agents' Last Exam | 25.7 | 25.2 | 16.5 | 15.8 | 23.8 | 27.6 | 25.7 | - |
| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 10.8 | 12.9 | 30.8 | 27.2 | 29.1 |
| DSBench-FullStack † | 71.1 | 68.7 | 41.8 | 37.0 | 61.8 | 73.7 | 71.6 | 77.2 |
| DSBench-Hard † | 67.2 | 59.6 | 31.1 | 25.8 | 54.5 | 63.0 | 71.7 | 68.3 |
Notes:
max reasoning effort level with temperature = 1.0, top_p = 0.95.This release does not include a Jinja-format chat template. Instead, we provide a dedicated encoding folder with Python scripts and test cases demonstrating how to encode messages in OpenAI-compatible format into input strings for the model, and how to parse the model's text output. Please refer to the encoding folder for full documentation.
The reasoning_effort parameter now supports three levels — low, high, and max — which control how much deliberation the model spends before answering.
A brief example:
from encoding_dsv4 import encode_messages, parse_message_from_completion_text
messages = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "Hello! I am DeepSeek.", "reasoning_content": "thinking..."},
{"role": "user", "content": "1+1=?"}
]
# messages -> string
prompt = encode_messages(messages, thinking_mode="thinking", reasoning_effort="max")
# string -> tokens
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro-0813")
tokens = tokenizer.encode(prompt)
DSpark speculative decoding is enabled with a single flag — add --speculative-config with method: dspark to your vLLM launch command:
--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
For example, the command below serves the model with vLLM on a single 4×GB300 node. See the vLLM recipe for detailed instructions and other hardware configurations.
vllm serve deepseek-ai/DeepSeek-V4-Pro-0813 \
--trust-remote-code --kv-cache-dtype fp8 --block-size 256 \
--data-parallel-size 4 --enable-expert-parallel \
--moe-backend deep_gemm_mega_moe \
--attention-config '{"use_fp4_indexer_cache": true}' \
--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
Enable DSpark with --speculative-algorithm DSPARK and do not set a separate --speculative-draft-model-path as the target and draft weights therefore come from the same checkpoint.
See the SGLang cookbook for detailed instructions, benchmarks and other hardwares configurations.
sglang serve \
--trust-remote-code \
--model-path deepseek-ai/DeepSeek-V4-Pro-0813 \
--tp 4 \
--moe-runner-backend flashinfer_mxfp4 \
--speculative-algorithm DSPARK \
--mem-fraction-static 0.90 \
--chunked-prefill-size 4096 \
--swa-full-tokens-ratio 0.1 \
Please refer to the inference folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.
For local deployment, we recommend setting the sampling parameters to temperature = 1.0, with top_p = 0.95 for agentic scenarios and top_p = 1.0 otherwise. For the high and max reasoning effort levels, we recommend a maximum output length of 384K tokens.
This repository and the model weights are licensed under the MIT License.
@misc{deepseekai2026deepseekv4,
title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence},
author={DeepSeek-AI},
year={2026},
}
If you have any questions, please raise an issue or contact us at [email protected].