update model

README.md

@@ -12,13 +12,13 @@ pipeline_tag: text-generation
 tags:
 - chat
 widget:
-- text: "<Human>: Hello <eoh> <Assistant>: "
+- text: "<Human>: Hello <eoh> <Assistant>:"
   example_title: "Hello"
-- text: "<Human>: 你好 <eoh> <Assistant>: "
+- text: "<Human>: 你好 <eoh> <Assistant>:"
   example_title: "你好"
-- text: "<Human>: What should I do if I can't sleep at night? <eoh> <Assistant>: "
+- text: "<Human>: What should I do if I can't sleep at night? <eoh> <Assistant>:"
   example_title: "insomnia"
-- text: "<Human>: 晚上睡不着应该怎么办？ <eoh> <Assistant>: "
+- text: "<Human>: 晚上睡不着应该怎么办？ <eoh> <Assistant>:"
   example_title: "失眠"
 inference:
   parameters:
@@ -42,7 +42,7 @@ tokenizer = AutoTokenizer.from_pretrained('nicholascao/chatbloom-1b7-sft')
 model = AutoModelForCausalLM.from_pretrained('nicholascao/chatbloom-1b7-sft').half()
 generation_config = GenerationConfig.from_pretrained('nicholascao/chatbloom-1b7-sft')
 
-inputs = tokenizer('<Human>: Hello <eoh> <Assistant>: ', return_tensors='pt').to(torch.cuda.current_device())
+inputs = tokenizer('<Human>: Hello <eoh> <Assistant>:', return_tensors='pt').to(torch.cuda.current_device())
 model.to(torch.cuda.current_device())
 
 output = model.generate(**inputs, generation_config=generation_config)

generation_config.json

@@ -4,7 +4,7 @@
   "do_sample": true,
   "early_stopping": true,
   "eos_token_id": 2,
-  "max_new_tokens": 384,
+  "max_new_tokens": 512,
   "pad_token_id": 2,
   "repetition_penalty": 1.1,
   "temperature": 0.8,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f55ca3cd52f4220e9046d88293c8b8cf65ea17e17c1c35a60c58941651a7fb
-size 3444055647
+oid sha256:076ce6313d3e4895c711440cf34ee5205223b9bd26286fa2fa41e9ce2f92579d
+size 3444055875