first commit

README.md

@@ -61,15 +61,15 @@ KeyError: 'qwen2'
 Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from modelscope import AutoModelForCausalLM, AutoTokenizer
 device = "cuda" # the device to load the model onto
 
 model = AutoModelForCausalLM.from_pretrained(
-    "study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4",
+    "huangjintao/Qwen1.5-110B-Chat-GPTQ-Int4",
     torch_dtype="auto",
     device_map="auto"
 )
-tokenizer = AutoTokenizer.from_pretrained("study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4")
+tokenizer = AutoTokenizer.from_pretrained("huangjintao/Qwen1.5-110B-Chat-GPTQ-Int4")
 
 prompt = "Give me a short introduction to large language model."
 messages = [

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4308dc5032f0bbe5924a2328b7ea2a05cfa5cf31374a5c39e8a9e109273ad0e2
+size 9846430896

model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843cc255d2425483f4d8c31e08196290c31bbb5a98d369c890f736211dea2148
-size 4096
+oid sha256:d4ca0343ac5a39bb9c0c2efb016d054fd61497fd4e905a2ee544438593978301
+size 9893790680

model-00005-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb4cd885ccde18ccf4e267d0c7b325e8cf520c14cfa280ba28f11b1336ca3f9
-size 2112454656
+oid sha256:f67601601dbad89557712b81d7d2cee5ba9f4149e18b6f6ea3e8919d44d74225
+size 9893790680