Merge branch 'main' into config_update_tests

examples/llama7b_sparse_quantized/README.md

@@ -40,7 +40,7 @@ run the following:
 
 ```
 import torch
-from sparseml import SparseAutoModelForCausalLM
+from sparseml.transformers import SparseAutoModelForCausalLM
 
 model = SparseAutoModelForCausalLM.from_pretrained(output_dir, torch_dtype=torch.bfloat16)
 model.save_pretrained(compressed_output_dir, save_compressed=True)
@@ -49,4 +49,4 @@ model.save_pretrained(compressed_output_dir, save_compressed=True)
 ### Custom Quantization
 The current repo supports multiple quantization techniques configured using a recipe. Supported strategies are `tensor`, `group` and `channel`. 
 The above recipe (`2:4_w4a16_recipe.yaml`) uses channel-wise quantization specified by `strategy: "channel"` in its config group. 
-To use quantize per tensor, change strategy from `channel` to `tensor`. To use group size quantization, change from `channel` to `group` and specify its value, say 128, by including `group_size: 128`. Group size quantization example is shown in `2:4_w4a16_group-128_recipe.yaml`
+To use quantize per tensor, change strategy from `channel` to `tensor`. To use group size quantization, change from `channel` to `group` and specify its value, say 128, by including `group_size: 128`. Group size quantization example is shown in `2:4_w4a16_group-128_recipe.yaml`