From 3be4415140c8a2e16faa21b1a45dc5ef856c17f9 Mon Sep 17 00:00:00 2001 From: "Dong, Bo" Date: Fri, 24 May 2024 15:47:32 +0800 Subject: [PATCH 1/2] Update README.md Signed-off-by: Dong, Bo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3cf77e28855..6a6d977b04f 100644 --- a/README.md +++ b/README.md @@ -219,7 +219,7 @@ inputs = tokenizer(prompt, return_tensors="pt").input_ids model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True) outputs = model.generate(inputs) ``` -You can also load GGUF format model from Huggingface, we only support Q4_0 gguf format for now. +You can also load GGUF format model from Huggingface, we only support Q4_0/Q8_0 gguf format for now. ```python from transformers import AutoTokenizer from intel_extension_for_transformers.transformers import AutoModelForCausalLM From 0565193e5ca7fba224afb7e3f4001e7199b6834b Mon Sep 17 00:00:00 2001 From: "Dong, Bo" Date: Fri, 24 May 2024 15:50:02 +0800 Subject: [PATCH 2/2] Update README.md Signed-off-by: Dong, Bo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6a6d977b04f..21aff495bb4 100644 --- a/README.md +++ b/README.md @@ -219,7 +219,7 @@ inputs = tokenizer(prompt, return_tensors="pt").input_ids model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True) outputs = model.generate(inputs) ``` -You can also load GGUF format model from Huggingface, we only support Q4_0/Q8_0 gguf format for now. +You can also load GGUF format model from Huggingface, we only support Q4_0/Q5_0/Q8_0 gguf format for now. ```python from transformers import AutoTokenizer from intel_extension_for_transformers.transformers import AutoModelForCausalLM