Update README.md

README.md

@@ -17,49 +17,40 @@ license: other
 </div>
 <!-- header end -->
 
-# Eric Hartford's WizardLM Uncensored Falcon 40B GGML
+# Eric Hartford's WizardLM Uncensored  Falcon 40B GGML
 
-These files are GGML format model files for [Eric Hartford's WizardLM Uncensored Falcon 40B](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b).
+These files are **experimental** GGML format model files for [Eric Hartford's WizardLM Uncensored  Falcon 40B](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b).
 
-GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
-* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
-* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
-* [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
-* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
-* [ctransformers](https://github.com/marella/ctransformers)
+These GGML files will **not** work in llama.cpp, and at the time of writing they will not work with any UI or library. They cannot be used from Python code.
+
+The can be used with a new fork of llama.cpp that adds Falcon GGML support: [cmp-nc/ggllm.cpp](https://github.com/cmp-nct/ggllm.cpp)
 
 ## Repositories available
 
-* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-GPTQ)
-* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-GGML)
-* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b)
+* [4-bit GPTQ model for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-GPTQ)
+* [3-bit GPTQ model for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-3bit-GPTQ).
+* [4 and 5-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-40B-GGML)
+* [Eric's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-40b)
 
 <!-- compatibility_ggml start -->
 ## Compatibility
 
-### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
-
-I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
-
-These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
-
-### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
-
-These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
+To build cmp-nct's fork of llama.cpp with Falcon 40B support plus preliminary CUDA acceleration, please follow the following steps:
 
-They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
+```
+git clone https://github.com/cmp-nct/ggllm.cpp
+cd ggllm.cpp
+git checkout cuda-integration
+rm -rf build && mkdir build && cd build && cmake -DGGML_CUBLAS=1 .. && cmake --build . --config Release
+```
 
-## Explanation of the new k-quant methods
+You can then use `bin/falcon_main` just like you would use llama.cpp. For example:
+```
+bin/falcon_main -t 1 -ngl 100 -m /workspace/wizard-falcon40b.ggmlv3.q3_K_S.bin -p "What is a falcon?\n### Response:"
+```
 
-The new methods available are:
-* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
-* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
-* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
-* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
-* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
-* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
+As with llama.cpp, if you can fully offload the model to VRAM you should use `-t 1` for maximum performance.  If not, use more threads, eg `-t 8`.
 
-Refer to the Provided Files table below to see what files use which methods, and how.
 <!-- compatibility_ggml end -->
 
 ## Provided files
@@ -76,26 +67,8 @@ Refer to the Provided Files table below to see what files use which methods, and
 | wizard-falcon40b.ggmlv3.q6_K.bin | q6_K | 6 | 34.33 GB | 36.83 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
 | wizard-falcon40b.ggmlv3.q8_0.bin | q8_0 | 8 | 44.46 GB | 46.96 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.
 
-## How to run in `llama.cpp`
-
-I use the following command line; adjust for your tastes and needs:
-
-```
-./main -t 10 -ngl 32 -m gpt4-x-alpaca-13b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
-```
-Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
-
-Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
-
-If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
-
-## How to run in `text-generation-webui`
-
-Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
-
 <!-- footer start -->
 ## Discord