--- inference: false license: other ---
TheBlokeAI

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

# Chtan's GPT4 Alpaca LoRA MLP 65B GGML These files are GGML format model files for [Chtan's GPT4 Alpaca LoRA MLP 65B](https://huggingface.co/chtan/gpt4-alpaca-lora_mlp-65b). 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) ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-GGML) * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-HF) ## 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`. They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README. ### 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 only compatible with llama.cpp as of June 6th, commit `2d43387`. They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days. ## Explanation of the new k-quant methods 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. Refer to the Provided Files table below to see what files use which methods, and how. ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q2_K.bin | q2_K | 2 | 27.33 GB | 29.83 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 34.55 GB | 37.05 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 31.40 GB | 33.90 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 28.06 GB | 30.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB | 39.23 GB | Original llama.cpp quant method, 4-bit. | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB | 43.31 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 39.28 GB | 41.78 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 36.73 GB | 39.23 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB | 47.39 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB | 51.47 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 46.20 GB | 48.70 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 | | gpt4-alpaca-lora_mlp-65B.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 44.89 GB | 47.39 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | **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-alpaca-lora_mlp-65B.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 ` 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). ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov. **Patreon special mentions**: Oscar Rangel, Eugene Pentland, Talal Aujan, Cory Kujawski, Luke, Asp the Wyvern, Ai Maven, Pyrater, Alps Aficionado, senxiiz, Willem Michiel, Junyu Yang, trip7s trip, Sebastain Graf, Joseph William Delisle, Lone Striker, Jonathan Leane, Johann-Peter Hartmann, David Flickinger, Spiking Neurons AB, Kevin Schuppel, Mano Prime, Dmitriy Samsonov, Sean Connelly, Nathan LeClaire, Alain Rossmann, Fen Risland, Derek Yates, Luke Pendergrass, Nikolai Manek, Khalefa Al-Ahmad, Artur Olbinski, John Detwiler, Ajan Kanaga, Imad Khwaja, Trenton Dambrowitz, Kalila, vamX, webtim, Illia Dulskyi. Thank you to all my generous patrons and donaters! # Original model card: Chtan's GPT4 Alpaca LoRA MLP 65B This repo provides the training checkpoint of LLaMA on the alpaca_data_gpt4 dataset via LoRA [MLP] on 8xA100(80G). He et al. 2022 gave an insight that FFN can better utilize modification at larger capacities. The codes is provided by [tloen/alpaca-lora: Instruct-tune LLaMA on consumer hardware (github.com)](https://github.com/tloen/alpaca-lora). We modify the running scripts to ```bash torchrun --nproc_per_node=8 finetune.py \ --base_model '/cache1/chtan/large_models/llama-hf/llama-65b' \ --data_path './alpaca_data_gpt4.json' \ --output_dir './gpt4-alpaca-lora_mlp-65b' \ --batch_size 128 \ --micro_batch_size 2 \ --num_epochs 10 \ --learning_rate 1e-4 \ --cutoff_len 512 \ --val_set_size 2000 \ --lora_r 16 \ --lora_alpha 16 \ --lora_dropout 0.05 \ --lora_target_modules '[gate_proj,down_proj,up_proj]' \ --train_on_inputs \ --group_by_length ``` ### Examples **Instruction**: Tell me about alpacas. **gpt4-alpaca-lora_mlp-65b**: Alpacas are small, domesticated mammals that are closely related to llamas. They are native to the Andes Mountains of South America, primarily in Peru, Bolivia, and Chile. These animals have been domesticated for thousands of years and were used by the Incas for their fleece, meat, and as pack animals. Alpacas are known for their soft and warm fleece, which comes in over 22 natural colors. Their fleece is highly valued and is used in the textile industry to make clothing and other products. Alpacas are also known for their friendly and gentle nature, making them popular pets and great additions to farms. These animals are social and live in herds, typically with one dominant male. They communicate through a series of hums, clucks, and other vocalizations. Alpacas are also known for their distinctive "humming" sound, which they make when they are content or curious. In terms of physical appearance, alpacas have a small, stocky build, with an average height of around 36 inches at the withers. They have large, expressive eyes, and their ears are perked forward. Alpacas are herbivores and primarily eat grasses and other vegetation. They are also known for their efficient digestive system, which allows them to thrive on a diet of low-quality forage. Overall, alpacas are unique and fascinating animals that have been an important part of Andean culture for centuries. They continue to be valued for their fleece, meat, and as pets, and their popularity continues to grow around the world. **Alpaca-LoRA**: Alpacas are members of the camelid family and are native to the Andes Mountains of South America. They are known for their soft, luxurious fleece, which is used to make clothing, blankets, and other items. Alpacas are herbivores and graze on grasses and other plants. They are social animals and live in herds of up to 20 individuals. **Stanford Alpaca**: Alpacas are small, fluffy animals related to camels and llamas. They are native to Peru and Bolivia, and were first domesticated around 5,000 years ago. They are kept mainly for their fine, soft fleece, which is used to make knitwear and other garments. Alpacas are herd animals and live in small family groups, led by an older male. They are highly social animals and can form strong bonds with their owners. **text-davinci-003**: Alpacas are a domesticated species of South American camelid, similar to llamas. They are native to the Andes Mountains in South America and are kept as livestock for their soft, luxurious wool. Alpacas are social animals and live in herds of up to 20 individuals. They are typically kept in small herds of two to five animals, and are relatively easy to care for. Alpacas are herbivores and feed on grass, hay, and other vegetation. They are also known for their gentle and friendly nature, making them popular as pets. --- **Instruction**: Write a Python program that prints the first 10 Fibonacci numbers. **gpt4-alpaca-lora_mlp-65b**: Here is a Python program that prints the first 10 Fibonacci numbers: ```python # initialize variables a = 0 b = 1 # loop to print the first 10 Fibonacci numbers for i in range(10): print(a, end=" ") a, b = b, a + b ``` In this program, we initialize two variables `a` and `b` with the first two Fibonacci numbers, which are 0 and 1. Then, we use a for loop to iterate 10 times. In each iteration, we print the current value of `a` and update the values of `a` and `b` using the formula `a = b` and `b = a + b`. This formula is the definition of the Fibonacci sequence. **Alpaca-LoRA**: ```python def fibonacci(n): if n == 0: return 0 elif n == 1: return 1 else: return fibonacci(n-1) + fibonacci(n-2) print(fibonacci(10)) ``` **Stanford Alpaca**: ```python numbers = [0, 1] for i in range(2, 11): numbers.append(numbers[i-2] + numbers[i-1]) print(numbers) # Output: [0, 1, 1, 2, 3, 5, 8, 13, 21, 34] ``` **text-davinci-003**: ```python # Fibonacci numbers are the numbers in the following integer sequence, called the Fibonacci sequence, and characterized by the fact that every number after the first two is the sum of the two preceding ones. # Fibonacci sequence: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ... # Program: # Initialize the first two numbers of the Fibonacci sequence a = 0 b = 1 # Print the first 10 numbers of the Fibonacci sequence print(a) print(b) for i in range(2,10): c = a + b a = b b = c print(c) ``` --- > [1] Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig: Towards a Unified View of Parameter-Efficient Transfer Learning. ICLR 2022