diff options
| author | Nexes the Elder <124105151+Nexesenex@users.noreply.github.com> | 2025-05-24 10:49:10 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-24 11:49:10 +0300 |
| commit | c7ecd4e23acb42f1150abf0b118e0a2c7b8dc959 (patch) | |
| tree | 6c619eb2d01abd3435f53bb092209935b252c8bb /src/llama.cpp | |
| parent | a2c42f9985a96abc8b1b4104b0524ea4b2da9363 (diff) | |
Legacy quants conversion schemes in convert_hf_to_gguf.py (#449)
* Legacy quants conversion schemes in convert_hf_to_gguf.py
This, notably in order to make smaller conversions to generate an iMatrix file.
`Q4_0`,`Q4_1` are here using embeddings, output, attn_k and attn_v in q5_0.
`Q5_0`,`Q5_1` are here using embeddings, output, attn_k and attn_v in q8_0.
Adapted from the following llama.cpp mainline PR : https://github.com/ggml-org/llama.cpp/pull/9022
Original author @chentyjpm
Also, 2 forgotten mentions of FTYPE IQ3_KL in llama.cpp file.
* forgotten IQ5_KS case mention
Diffstat (limited to 'src/llama.cpp')
| -rw-r--r-- | src/llama.cpp | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/src/llama.cpp b/src/llama.cpp index 48d7214d..0a620164 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -18803,7 +18803,8 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS_R4) { new_type = !qs.has_output ? GGML_TYPE_IQ4_K_R4 : GGML_TYPE_Q5_K_R4; } - else if ((ftype == LLAMA_FTYPE_MOSTLY_IQ3_S || ftype == LLAMA_FTYPE_MOSTLY_IQ3_M || ftype == LLAMA_FTYPE_MOSTLY_IQ4_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ3_S_R4 || + else if ((ftype == LLAMA_FTYPE_MOSTLY_IQ3_S || ftype == LLAMA_FTYPE_MOSTLY_IQ3_M || ftype == LLAMA_FTYPE_MOSTLY_IQ3_KL || + ftype == LLAMA_FTYPE_MOSTLY_IQ4_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ3_S_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ4_KS || ftype == LLAMA_FTYPE_MOSTLY_IQ4_KSS || ftype == LLAMA_FTYPE_MOSTLY_IQ4_KS_R4) && !qs.has_output) { new_type = GGML_TYPE_IQ5_K; } @@ -19165,8 +19166,8 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n ftype == LLAMA_FTYPE_MOSTLY_IQ3_M || ftype == LLAMA_FTYPE_MOSTLY_IQ4_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ4_K || ftype == LLAMA_FTYPE_MOSTLY_IQ4_KSS || ftype == LLAMA_FTYPE_MOSTLY_IQ4_KS || ftype == LLAMA_FTYPE_MOSTLY_IQ4_KS_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ5_KS || ftype == LLAMA_FTYPE_MOSTLY_IQ5_KS_R4 || - ftype == LLAMA_FTYPE_MOSTLY_IQ2_K || ftype == LLAMA_FTYPE_MOSTLY_IQ3_K || ftype == LLAMA_FTYPE_MOSTLY_Q4_K_R4 || - ftype == LLAMA_FTYPE_MOSTLY_IQ4_NL_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ4_XS_R8 || + ftype == LLAMA_FTYPE_MOSTLY_IQ2_K || ftype == LLAMA_FTYPE_MOSTLY_IQ3_K || ftype == LLAMA_FTYPE_MOSTLY_IQ3_KL || + ftype == LLAMA_FTYPE_MOSTLY_Q4_K_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ4_NL_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ4_XS_R8 || ftype == LLAMA_FTYPE_MOSTLY_Q3_K_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ3_KT || ftype == LLAMA_FTYPE_MOSTLY_Q2_K_R4|| ftype == LLAMA_FTYPE_MOSTLY_IQ4_K_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ3_K_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ2_K_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4 || ftype == LLAMA_FTYPE_MOSTLY_IQ3_S_R4) { |