sleepy/llama.cpp
1
0
Fork 0
Code Issues 9 Pull Requests Actions 103 Packages Projects Releases Wiki Activity

convert : Handle ModelOpt produced mixed precision model during convert to GGUF (#22247)

Browse Source 
* Handle ModelOpt produced mixed precision model during convert to GGUF

* Apply suggestions from code review

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

* Apply suggestions from code review

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
ynankani
2026-04-23 05:19:51 +00:00
committed by GitHub
parent 60b68a6279
commit 5eaee65384
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
convert_hf_to_gguf.py
+6 -1
View File
@@ -746,7 +746,12 @@ class ModelBase:
if (not quant_algo or not quant_layers) and quant_config_file.is_file(): if (not quant_algo or not quant_layers) and quant_config_file.is_file():
with open(quant_config_file, "r", encoding="utf-8") as f: with open(quant_config_file, "r", encoding="utf-8") as f:
quant_config = json.load(f).get("quantization") or {} hf_quant_config = json.load(f)
quant_config = hf_quant_config.get("quantization") or {}
producer = hf_quant_config.get("producer") or {}
producer_name = (producer.get("name") or "").lower()
if quant_method is None:
self.hparams.setdefault("quantization_config", {})["quant_method"] = producer_name
quant_algo = quant_config.get("quant_algo", quant_algo) quant_algo = quant_config.get("quant_algo", quant_algo)
quant_layers = quant_config.get("quantized_layers", quant_layers) or {} quant_layers = quant_config.get("quantized_layers", quant_layers) or {}