Upload README.md

README.md

@@ -33,14 +33,14 @@ quantized_by: fbaldassarri
 ## Model Information
 
 Quantized version of [tiiuae/Falcon3-10B-Instruct](https://huggingface.co/tiiuae/Falcon3-10B-Instruct) using torch.float32 for quantization tuning.
-- 4 bits (INT4)
+- 8 bits (INT8)
 - group size = 128
 - Asymmetrical Quantization
 - Method AutoGPTQ
 
-Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.4
+Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.5
 
-Note: this INT4 version of Falcon3-10B-Instruct has been quantized to run inference through CPU.
+Note: this INT8 version of Falcon3-10B-Instruct has been quantized to run inference through CPU.
 
 ## Replication Recipe
 
@@ -49,9 +49,9 @@ Note: this INT4 version of Falcon3-10B-Instruct has been quantized to run infere
 I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment. 
 
 ```
-wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.4.tar.gz
-tar -xvzf v0.4.4.tar.gz
-cd auto-round-0.4.4
+wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.5.tar.gz
+tar -xvzf v0.4.5.tar.gz
+cd auto-round-0.4.5
 pip install -r requirements-cpu.txt --upgrade
 ```
 
@@ -69,10 +69,10 @@ pip install -vvv --no-build-isolation -e .[cpu]
   model = AutoModelForCausalLM.from_pretrained(model_name)
   tokenizer = AutoTokenizer.from_pretrained(model_name)
   from auto_round import AutoRound
-  bits, group_size, sym, device, amp = 4, 128, False, 'cpu', False
+  bits, group_size, sym, device, amp = 8, 128, False, 'cpu', False
   autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
   autoround.quantize()
-  output_dir = "./AutoRound/tiiuae_Falcon3-10B-Instruct-autogptq-int4-gs128-asym"
+  output_dir = "./AutoRound/tiiuae_Falcon3-10B-Instruct-autogptq-int8-gs128-asym"
   autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
 ```