convert : Handle ModelOpt produced mixed precision model during convert to GGUF ...

* Handle ModelOpt produced mixed precision model during convert to GGUF

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <redacted>
* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

Co-authored-by: Sigbjørn Skjæret <redacted>

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 090686b1531295435169b34ed49ca72d12b264d2..93d5509e6af6f48692025d0ebe525363f1812002 100755 (executable)
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -746,7 +746,12 @@ class ModelBase:
 
         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:
-                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_layers = quant_config.get("quantized_layers", quant_layers) or {}