diff --git a/README.md b/README.md index 0b6bac5..e8db97e 100644 --- a/README.md +++ b/README.md @@ -160,7 +160,7 @@ huggingface-cli download 1bitLLM/bitnet_b1_58-large --local-dir models/bitnet_b1 python setup_env.py -md models/bitnet_b1_58-large -q i2_s ```
-usage: setup_env.py [-h] [--hf-repo {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}] [--model-dir MODEL_DIR] [--log-dir LOG_DIR] [--quant-type {i2_s,tl1}] [--quant-embd]
+usage: setup_env.py [-h] [--hf-repo {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}] [--model-dir MODEL_DIR] [--log-dir LOG_DIR] [--quant-type {i2_s,tl1,tl2,tl2-loss}] [--quant-embd]
                     [--use-pretuned]
 
 Setup the environment for running inference
@@ -173,7 +173,7 @@ optional arguments:
                         Directory to save/load the model
   --log-dir LOG_DIR, -ld LOG_DIR
                         Directory to save the logging info
-  --quant-type {i2_s,tl1}, -q {i2_s,tl1}
+  --quant-type {i2_s,tl1,tl2,tl2-loss}, -q {i2_s,tl1,tl2,tl2-loss}
                         Quantization type
   --quant-embd          Quantize the embeddings to f16
   --use-pretuned, -p    Use the pretuned kernel parameters