mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

convert : Mistral format yarn apply_scale support (#22612)

Browse Source 
* [BUGFIX] Mistral format apply_scale support.

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix misunderstood boolean parameters

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Julien Denize
2026-05-03 21:51:21 +02:00
committed by GitHub
parent db44417b02
commit 048a490f76
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
convert_hf_to_gguf.py
+2 -1
View File
@@ -12716,11 +12716,12 @@ class MistralModel(LlamaModel):
def set_mistral_config(gguf_writer: gguf.GGUFWriter, hparams: dict):
if "yarn" in hparams:
yarn_params = hparams["yarn"]
mscale_all_dim = 1.0 if not yarn_params["apply_scale"] else 0.0
gguf_writer.add_rope_scaling_type(gguf.RopeScalingType.YARN)
gguf_writer.add_rope_scaling_factor(yarn_params["factor"])
gguf_writer.add_rope_scaling_yarn_beta_fast(yarn_params["beta"])
gguf_writer.add_rope_scaling_yarn_beta_slow(yarn_params["alpha"])
gguf_writer.add_rope_scaling_yarn_log_mul(1.0) # mscale_all_dim
gguf_writer.add_rope_scaling_yarn_log_mul(mscale_all_dim)
gguf_writer.add_rope_scaling_orig_ctx_len(yarn_params["original_max_position_embeddings"])
if "llama_4_scaling" in hparams: