You can deploy this model and start earning money today!

forkjoin-ai/
llama-70b-rknot

Name: llama-70b-rknot
Availability: InStock

meta-llama/Meta-Llama-3-70B-Instruct

finetune

apache-2.0

Views

No views yet

llama-70b — Resonance Knot (`.rknot`)

Spectral-residual repack of the dense .knot weight format. Drops non-standing-wave embedding dimensions, signed-quantizes the rest at amplitude-graded bit widths, ships as a single .rknot file with a header pointer table for mmap-style block access.

Compression

Artifact	Bytes	Notes
Resonance Knot `.rknot`	4790725830 (4.46 GiB)	spectral-residual repack of the dense Q4_K_M `.knot`

Quantization profile (production defaults):

standing-wave coverage k = 0.30 × hidden_dim
Q/K: 4 bits, signed, per-block scale
V: 8 bits, signed, per-block scale
FFN: 4 bits, signed, per-block scale

Format

magic        :  6 bytes  RKNOT\\x02
header_len   :  4 bytes  u32 LE
header_json  :  N bytes  manifest, per-layer pointers, arch metadata
body         :  rest     concatenated quantized blocks

Generated by the forkjoin-ai/distributed-inference Cloud Build pipeline.

forkjoin-ai/llama-70b-rknot

llama-70b — Resonance Knot (.rknot)

Compression

Format

forkjoin-ai/
llama-70b-rknot

llama-70b — Resonance Knot (`.rknot`)