Initial GGML model commit

README.md

@@ -31,17 +31,8 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
 ## Repositories available
 
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-30B-GPTQ)
-* [4-bit, 5-bit and 8-bit GGML models for CPU(+GPU) inference](https://huggingface.co/TheBloke/WizardLM-30B-GGML)
-* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/WizardLM-30B-fp16)
-
-## Prompt template
-
-```
-A chat between a curious user and an artificial intelligence assistant.
-The assistant gives helpful, detailed, and polite answers to the user's questions.
-USER: prompt goes here
-ASSISTANT:
-```
+* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-30B-GGML)
+* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardLM-30B-V1.0)
 
 <!-- compatibility_ggml start -->
 ## Compatibility
@@ -87,6 +78,7 @@ Refer to the Provided Files table below to see what files use which methods, and
 | wizardlm-30b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.02 GB | 25.52 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
 | wizardlm-30b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.37 GB | 24.87 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
 | wizardlm-30b.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB | 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
+| wizardlm-30b.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB | 37.06 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
 
 
 **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.