update: cicd

awq-py/README.md

@@ -4,7 +4,7 @@
 **Supported models:**
 
 - [X] LLaMA
-- [x] LLaMA 2 
+- [x] LLaMA 2
 - [X] MPT
 - [X] Mistral AI v0.1
 - [ ] Bloom
@@ -33,7 +33,7 @@ Install requirements
 pip install -r requirements.txt
 ```
 Get the pre-computed AWQ search results for multiple model families, including LLaMA, LLaMA2, MPT, OPT
-```bash 
+```bash
 git clone https://huggingface.co/datasets/mit-han-lab/awq-model-zoo awq_cache
 ```
 

awq-py/awq/apply_awq.py

@@ -170,7 +170,7 @@ def apply_scale(module, scales_list, input_feat_dict=None):
     Args:
         module (nn.Module): The module containing the layers to be scaled.
         scales_list (List[Tuple[str, List[str], torch.Tensor]]): A list of tuples containing:
-            * prev_op_name (str): The name of the preceding operation or module, 
+            * prev_op_name (str): The name of the preceding operation or module,
                 relative to which the layers to be scaled are located.
             * layer_names (List[str]): A list of names of the layers to be scaled, relative to the preceding operation.
             * scales (torch.Tensor): A 1D tensor of size (num_features,) containing the scaling factors for each feature.
@@ -237,7 +237,7 @@ def apply_clip(module, clip_list):
 
 def add_scale_weights(model_path, scale_path, tmp_path):
     """
-    Adds pre-computed Activation Weight Quantization (AWQ) results to a model, 
+    Adds pre-computed Activation Weight Quantization (AWQ) results to a model,
     including scaling factors and clipping bounds.
 
     Args:

awq-py/requirements.txt

@@ -1,2 +1,2 @@
 torch>=2.0.0
-transformers>=4.32.0
+transformers>=4.32.0

convert-hf-to-gguf.py

@@ -1041,7 +1041,7 @@ dir_model = args.model
 
 if args.awq_path:
     sys.path.insert(1, str(Path(__file__).parent / 'awq-py'))
-    from awq.apply_awq import add_scale_weights     
+    from awq.apply_awq import add_scale_weights    
     tmp_model_path = args.model / "weighted_model"
     dir_model = tmp_model_path
     if tmp_model_path.is_dir():
@@ -1050,7 +1050,7 @@ if args.awq_path:
         tmp_model_path.mkdir(parents=True, exist_ok=True)
         print("Saving new weighted model ...")
         add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path))
-        print(f"Saved weighted model at {tmp_model_path}.") 
+        print(f"Saved weighted model at {tmp_model_path}.")
 
 if not dir_model.is_dir():
     print(f'Error: {args.model} is not a directory', file=sys.stderr)

convert.py

@@ -1201,7 +1201,7 @@ def main(args_in: list[str] | None = None) -> None:
     args = parser.parse_args(args_in)
     if args.awq_path:
         sys.path.insert(1, str(Path(__file__).parent / 'awq-py'))
-        from awq.apply_awq import add_scale_weights        
+        from awq.apply_awq import add_scale_weights
         tmp_model_path = args.model / "weighted_model"
         if tmp_model_path.is_dir():
             print(f"{tmp_model_path} exists as a weighted model.")
@@ -1209,9 +1209,9 @@ def main(args_in: list[str] | None = None) -> None:
             tmp_model_path.mkdir(parents=True, exist_ok=True)
             print("Saving new weighted model ...")
             add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path))
-            print(f"Saved weighted model at {tmp_model_path}.") 
+            print(f"Saved weighted model at {tmp_model_path}.")
         args.model = tmp_model_path
-    
+
     if args.dump_single:
         model_plus = lazy_load_file(args.model)
         do_dump_model(model_plus)

gguf-py/gguf/tensor_mapping.py

@@ -180,7 +180,7 @@ class TensorNameMap:
             "layers.{bid}.feed_forward.experts.{xid}.w3",           # mixtral
             "model.layers.{bid}.block_sparse_moe.experts.{xid}.w3", # mixtral
         ),
-        
+
         # AWQ-activation gate
         MODEL_TENSOR.FFN_ACT: (
             "transformer.blocks.{bid}.ffn.act",  # mpt