DeepSeek-V4-Flash-0731-FP8-PTPC – AI Model by ginsongsong | AlphaNeural AI

You can deploy this model and start earning money today!

ginsongsong/
DeepSeek-V4-Flash-0731-FP8-PTPC

like

0

deepseek-ai/DeepSeek-V4-Flash-0731

Views

No views yet

DeepSeek-V4-Flash-FP8

FP8 (block-wise e4m3 + f32 scale, 128×128 block) repackaging of deepseek-ai/DeepSeek-V4-Flash-0731.

What this is

The source checkpoint mixes three storage formats:

MXFP4 (FP4 packed in int8 + E8M0 scale) — routed experts only
MXFP8 (F8_E4M3 + E8M0 scale) — attention, shared experts, MTP
BF16 / F32 — norms, embeddings, gates

This repo unifies everything into a single block-wise FP8 layout so the model can run through one FP8 kernel path.

Conversion

Tensor	Source	Target
`ffn.experts.*.{w1,w2,w3}`	int8 (FP4) + E8M0 scale	F8_E4M3 + F32 scale
`attn.`, `shared_experts.`, `mtp.*.e_proj`	F8_E4M3 + E8M0 scale	F8_E4M3 + F32 scale (weight unchanged)
`attn.wo_a.weight`	F8_E4M3 + E8M0 scale	BF16 (scale absorbed)
`attn.wo_a.scale`	E8M0	dropped
norms, embed, gate, etc.	BF16 / F32	unchanged