Update README.md

README.md

@@ -3,7 +3,9 @@ datasets:
 - NeelNanda/pile-10k
 base_model:
 - deepseek-ai/DeepSeek-V3
+
 ---
+
 ## Model Details
 
 This model is an int4 model with group_size 128 and symmetric quantization of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. 
@@ -16,18 +18,32 @@ Please follow the license of the original model.
 
 ## How To Use
 
-### INT4 Inference
+### INT4 Inference on CPU with Qbits
 
-````python
+INT4 Inference on CPU with Qbits
+
+pip3 install auto-round **(it will install intel-extension-for-pytorch and intel-extension-for-transformers both)**. For intel cpu, it will use intel-extension-for-pytorch , for others, it will use intel-extension-for-transformers.
+
+**To make sure to use qbits with intel-extension-for-transformers, please uninstall intel-extension-for-pytorch, which we have not tested for this model yet.**
+
+
+
+~~~python
+from auto_round import AutoRoundConfig ##must import for autoround format
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-gptq-inc-preview"
 
+quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-gptq-inc-preview"
+quantization_config = AutoRoundConfig(
+    backend="cpu"
+)
 model = AutoModelForCausalLM.from_pretrained(
     quantized_model_dir,
     torch_dtype=torch.float16,
     trust_remote_code=True,
-    device_map="auto"
+    device_map="cpu",
+    revision="8fe0735",##use autoround format, the only difference is config.json
+    quantization_config = quantization_config, ##cpu only machine could not set this
     
 )
 
@@ -56,8 +72,6 @@ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)
 
-
-## The following result is inferred on CPU with qbits backend
 prompt = "9.11和9.8哪个数字大"  
 
 ##INT4
@@ -146,8 +160,50 @@ prompt = "There is a girl who likes adventure,"
 prompt = "Please give a brief introduction of DeepSeek company."
 ##INT4:
 """DeepSeek Artificial Intelligence Co., Ltd. (referred to as "DeepSeek" or "深度求索") , founded in 2023, is a Chinese company dedicated to making AGI a reality"""
+~~~
+
 
 
+### INT4 Inference on CUDA(have not tested, maybe need 8X80G GPU)
+
+````python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-gptq-inc-preview"
+
+model = AutoModelForCausalLM.from_pretrained(
+    quantized_model_dir,
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+    device_map="auto"
+    
+)
+
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir,trust_remote_code=True)
+prompt = "There is a girl who likes adventure,"
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=200,  ##change this to align with the official usage
+    do_sample=False  ##change this to align with the official usage
+)
+generated_ids = [
+output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+
 ````
 
 ### Evaluate the model