Upload new GPTQs with varied parameters

README.md

@@ -1,6 +1,7 @@
 ---
 inference: false
 license: other
+model_type: llama
 ---
 
 <!-- header start -->
@@ -39,7 +40,6 @@ Below is an instruction that describes a task. Write a response that appropriate
 ### Instruction: {prompt}
 
 ### Response:
-
 ```
 
 ## Provided files
@@ -53,7 +53,7 @@ Each separate quant is in a different branch.  See below for instructions on fet
 | main | 4 | 128 | False | 7.90 GB | True | GPTQ-for-LLaMa | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
 | gptq-4bit-32g-actorder_True | 4 | 32 | True | 8.45 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
 | gptq-4bit-64g-actorder_True | 4 | 64 | True | 7.95 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
-| gptq-4bit-128g-actorder_True | 4 | 128 | True | 7.70 GB | True | AutoGPTQ | 4-bit, with Act Order androup size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
+| gptq-4bit-128g-actorder_True | 4 | 128 | True | 7.70 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
 | gptq-8bit--1g-actorder_True | 8 | None | True | 13.80 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
 | gptq-8bit-128g-actorder_False | 8 | 128 | False | 14.10 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
 
@@ -130,7 +130,6 @@ prompt_template=f'''Below is an instruction that describes a task. Write a respo
 ### Instruction: {prompt}
 
 ### Response:
-
 '''
 
 print("\n\n*** Generate:")