Skip to content
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

Jump to bottom

Update GGUF docs #775

Merged
merged 2 commits into from Mar 27, 2024
Merged

Update GGUF docs #775

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2e075bf
spec: add missing semicolons in GGUF structs
JacobLinCool Mar 27, 2024
45729b8
spec: update GGUF tensor types
JacobLinCool Mar 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
52 changes: 31 additions & 21 deletions docs/gguf.md
View file
Open in desktop
Expand Up @@ -31,26 +31,36 @@ Models are little-endian by default. They can also come in big-endian for use wi

```c
enum ggml_type: uint32_t {
GGML_TYPE_F32 = 0,
GGML_TYPE_F16 = 1,
GGML_TYPE_Q4_0 = 2,
GGML_TYPE_Q4_1 = 3,
GGML_TYPE_F32 = 0,
GGML_TYPE_F16 = 1,
GGML_TYPE_Q4_0 = 2,
GGML_TYPE_Q4_1 = 3,
// GGML_TYPE_Q4_2 = 4, support has been removed
// GGML_TYPE_Q4_3 (5) support has been removed
GGML_TYPE_Q5_0 = 6,
GGML_TYPE_Q5_1 = 7,
GGML_TYPE_Q8_0 = 8,
GGML_TYPE_Q8_1 = 9,
// k-quantizations
GGML_TYPE_Q2_K = 10,
GGML_TYPE_Q3_K = 11,
GGML_TYPE_Q4_K = 12,
GGML_TYPE_Q5_K = 13,
GGML_TYPE_Q6_K = 14,
GGML_TYPE_Q8_K = 15,
GGML_TYPE_I8,
GGML_TYPE_I16,
GGML_TYPE_I32,
// GGML_TYPE_Q4_3 = 5, support has been removed
GGML_TYPE_Q5_0 = 6,
GGML_TYPE_Q5_1 = 7,
GGML_TYPE_Q8_0 = 8,
GGML_TYPE_Q8_1 = 9,
GGML_TYPE_Q2_K = 10,
GGML_TYPE_Q3_K = 11,
GGML_TYPE_Q4_K = 12,
GGML_TYPE_Q5_K = 13,
GGML_TYPE_Q6_K = 14,
GGML_TYPE_Q8_K = 15,
GGML_TYPE_IQ2_XXS = 16,
GGML_TYPE_IQ2_XS = 17,
GGML_TYPE_IQ3_XXS = 18,
GGML_TYPE_IQ1_S = 19,
GGML_TYPE_IQ4_NL = 20,
GGML_TYPE_IQ3_S = 21,
GGML_TYPE_IQ2_S = 22,
GGML_TYPE_IQ4_XS = 23,
GGML_TYPE_I8 = 24,
GGML_TYPE_I16 = 25,
GGML_TYPE_I32 = 26,
GGML_TYPE_I64 = 27,
GGML_TYPE_F64 = 28,
GGML_TYPE_IQ1_M = 29,
GGML_TYPE_COUNT,
};

Expand Down Expand Up @@ -85,15 +95,15 @@ enum gguf_metadata_value_type: uint32_t {
GGUF_METADATA_VALUE_TYPE_INT64 = 11,
// The value is a 64-bit IEEE754 floating point number.
GGUF_METADATA_VALUE_TYPE_FLOAT64 = 12,
}
};

// A string in GGUF.
struct gguf_string_t {
// The length of the string, in bytes.
uint64_t len;
// The string as a UTF-8 non-null-terminated string.
char string[len];
}
};

union gguf_metadata_value_t {
uint8_t uint8;
Expand Down