From 436504c6852495819328871ef556edaca7662c12 Mon Sep 17 00:00:00 2001 From: Camille Zhong <44392324+Camille7777@users.noreply.github.com> Date: Sat, 6 Jan 2024 17:00:32 +0800 Subject: [PATCH 1/2] Update README.md --- applications/Colossal-LLaMA-2/README.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/applications/Colossal-LLaMA-2/README.md b/applications/Colossal-LLaMA-2/README.md index 8fb55defaf2a..5242c7adf5c5 100644 --- a/applications/Colossal-LLaMA-2/README.md +++ b/applications/Colossal-LLaMA-2/README.md @@ -216,6 +216,7 @@ inputs = inputs.to('cuda:0') pred = model.generate(**inputs, max_new_tokens=256, do_sample=True, + temperature=0.3, top_k=50, top_p=0.95, num_return_sequences=1) @@ -233,12 +234,12 @@ model_dir = snapshot_download('colossalai/Colossal-LLaMA-2-13b-base', revision=' tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True).eval() -generation_kwargs = {"max_new_tokens": 256, - "top_p": 0.95, +generation_kwargs = {"max_new_tokens": 256, + "top_p": 0.95, "temperature": 0.3 } -input = '离离原上草，\n\n->\n\n' +input = '明月松间照，\n\n->\n\n' inputs = tokenizer(input, return_token_type_ids=False, return_tensors='pt') inputs = inputs.to('cuda:0') output = model.generate(**inputs, **generation_kwargs) From 4e7a0de77152223694afc490bf18ea3be68208a2 Mon Sep 17 00:00:00 2001 From: Camille Zhong <44392324+Camille7777@users.noreply.github.com> Date: Sat, 6 Jan 2024 17:03:41 +0800 Subject: [PATCH 2/2] Update README.md --- applications/Colossal-LLaMA-2/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/applications/Colossal-LLaMA-2/README.md b/applications/Colossal-LLaMA-2/README.md index 5242c7adf5c5..70185386382c 100644 --- a/applications/Colossal-LLaMA-2/README.md +++ b/applications/Colossal-LLaMA-2/README.md @@ -234,8 +234,8 @@ model_dir = snapshot_download('colossalai/Colossal-LLaMA-2-13b-base', revision=' tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True).eval() -generation_kwargs = {"max_new_tokens": 256, - "top_p": 0.95, +generation_kwargs = {"max_new_tokens": 256, + "top_p": 0.95, "temperature": 0.3 }