Update README.md

README.md

@@ -13,9 +13,9 @@ tags:
 - gptq
 - intel
 license: apache-2.0
-model_name: Minerva 1B base v1.0
+model_name: Minerva 350M base v1.0
 base_model: 
-- sapienzanlp/Minerva-1B-base-v1.0
+- sapienzanlp/Minerva-350M-base-v1.0
 inference: false
 model_creator: sapienzanlp
 datasets:
@@ -28,7 +28,7 @@ quantized_by: fbaldassarri
 
 ## Model Information
 
-Quantized version of [sapienzanlp/Minerva-1B-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-1B-base-v1.0) using torch.float32 for quantization tuning.
+Quantized version of [sapienzanlp/Minerva-350M-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-350M-base-v1.0) using torch.float32 for quantization tuning.
 - 8 bits (INT8)
 - group size = 128
 - Symmetrical Quantization
@@ -38,7 +38,7 @@ Fast and low memory, 2-3X speedup (slight accuracy drop at W8G128)
 
 Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.6
 
-Note: this INT8 version of Minerva-1B-base-v1.0 has been quantized to run inference through CPU.
+Note: this INT8 version of Minerva-350M-base-v1.0 has been quantized to run inference through CPU.
 
 ## Replication Recipe
 
@@ -63,14 +63,14 @@ pip install -vvv --no-build-isolation -e .[cpu]
 
 ```
   from transformers import AutoModelForCausalLM, AutoTokenizer
-  model_name = "sapienzanlp/Minerva-1B-base-v1.0"
+  model_name = "sapienzanlp/Minerva-350M-base-v1.0"
   model = AutoModelForCausalLM.from_pretrained(model_name)
   tokenizer = AutoTokenizer.from_pretrained(model_name)
   from auto_round import AutoRound
   bits, group_size, sym, device, amp = 8, 128, True, '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/sapienzanlp_Minerva-1B-base-v1.0-autoround-int8-gs128-sym"
+  output_dir = "./AutoRound/sapienzanlp_Minerva-350M-base-v1.0-autoround-int8-gs128-sym"
   autoround.save_quantized(output_dir, format='auto_round', inplace=True)
 ```