Skip to content

[gguf] Add source for IQ4_NL description #619

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 11, 2024
Merged

[gguf] Add source for IQ4_NL description #619

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions packages/gguf/src/quant-descriptions.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,35 +10,35 @@ export const GGUF_QUANT_DESCRIPTIONS: Record<GGMLQuantizationType, { txt: string
src_url: "https://en.wikipedia.org/wiki/Half-precision_floating-point_format",
},
[GGMLQuantizationType.Q4_0]: {
txt: "4-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale. Legacy quantization method (not used widely as of today)",
txt: "4-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale. Legacy quantization method (not used widely as of today).",
src_url: "https://github.com/huggingface/huggingface.js/pull/615#discussion_r1557654249",
},
[GGMLQuantizationType.Q4_1]: {
txt: "4-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale + block_minimum. Legacy quantization method (not used widely as of today)",
txt: "4-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale + block_minimum. Legacy quantization method (not used widely as of today).",
src_url: "https://github.com/huggingface/huggingface.js/pull/615#discussion_r1557682290",
},
[GGMLQuantizationType.Q5_0]: {
txt: "5-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale. Legacy quantization method (not used widely as of today)",
txt: "5-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale. Legacy quantization method (not used widely as of today).",
src_url: "https://github.com/huggingface/huggingface.js/pull/615#discussion_r1557654249",
},
[GGMLQuantizationType.Q5_1]: {
txt: "5-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale + block_minimum. Legacy quantization method (not used widely as of today)",
txt: "5-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale + block_minimum. Legacy quantization method (not used widely as of today).",
src_url: "https://github.com/huggingface/huggingface.js/pull/615#discussion_r1557682290",
},
[GGMLQuantizationType.Q8_0]: {
txt: "8-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale. Legacy quantization method (not used widely as of today)",
txt: "8-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale. Legacy quantization method (not used widely as of today).",
src_url: "https://github.com/huggingface/huggingface.js/pull/615#discussion_r1557654249",
},
[GGMLQuantizationType.Q8_1]: {
txt: "8-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale + block_minimum. Legacy quantization method (not used widely as of today)",
txt: "8-bit round-to-nearest quantization (q). Each block has 32 weights. Weight formula: w = q * block_scale + block_minimum. Legacy quantization method (not used widely as of today).",
src_url: "https://github.com/huggingface/huggingface.js/pull/615#discussion_r1557682290",
},
[GGMLQuantizationType.Q2_K]: {
txt: `2-bit quantization (q). Super-blocks with 16 blocks, each block has 16 weight. Weight formula: w = q * block_scale(4-bit) + block_min(4-bit), resulting in 2.5625 bits-per-weight.`,
src_url: "https://github.com/ggerganov/llama.cpp/pull/1684#issue-1739619305",
},
[GGMLQuantizationType.Q3_K]: {
txt: `3-bit quantization (q). Super-blocks with 16 blocks, each block has 16 weights. Weight formula: w = q * block_scale(6-bit), resulting. 3.4375 bits-per-weight`,
txt: `3-bit quantization (q). Super-blocks with 16 blocks, each block has 16 weights. Weight formula: w = q * block_scale(6-bit), resulting. 3.4375 bits-per-weight.`,
src_url: "https://github.com/ggerganov/llama.cpp/pull/1684#issue-1739619305",
},
[GGMLQuantizationType.Q4_K]: {
Expand Down Expand Up @@ -78,7 +78,8 @@ export const GGUF_QUANT_DESCRIPTIONS: Record<GGMLQuantizationType, { txt: string
"https://huggingface.co/CISCai/OpenCodeInterpreter-DS-6.7B-SOTA-GGUF/blob/main/README.md?code=true#L59-L70",
},
[GGMLQuantizationType.IQ4_NL]: {
txt: "4-bit quantization (q). Super-blocks with 256 weights. Weight w is obtained using super_block_scale & importance matrix",
txt: "4-bit quantization (q). Super-blocks with 256 weights. Weight w is obtained using super_block_scale & importance matrix.",
src_url: "https://github.com/ggerganov/llama.cpp/pull/5590",
},
[GGMLQuantizationType.IQ3_S]: {
txt: "3-bit quantization (q). Super-blocks with 256 weights. Weight w is obtained using super_block_scale & importance matrix, resulting in 3.44 bits-per-weight.",
Expand Down