TheBloke's picture
Update Readme to Correct 3x Typos in "VMware" (#1)
ffcff16
metadata
inference: false
license: other
TheBlokeAI

VMware's open-llama-7B-open-instruct GGML

These files are GGML format model files for VMware's open-llama-7B-open-instruct.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

Repositories available

Prompt template

Standard Alpaca:

Below is an instruction that describes a task. Write a response that appropriately completes the request

### Instruction: prompt
### Response:

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
open-llama-7B-open-instruct.ggmlv3.q2_K.bin q2_K 2 2.80 GB 5.30 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.
open-llama-7B-open-instruct.ggmlv3.q3_K_L.bin q3_K_L 3 3.55 GB 6.05 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
open-llama-7B-open-instruct.ggmlv3.q3_K_M.bin q3_K_M 3 3.23 GB 5.73 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
open-llama-7B-open-instruct.ggmlv3.q3_K_S.bin q3_K_S 3 2.90 GB 5.40 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
open-llama-7B-open-instruct.ggmlv3.q4_0.bin q4_0 4 3.79 GB 6.29 GB Original llama.cpp quant method, 4-bit.
open-llama-7B-open-instruct.ggmlv3.q4_1.bin q4_1 4 4.21 GB 6.71 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.
open-llama-7B-open-instruct.ggmlv3.q4_K_M.bin q4_K_M 4 4.05 GB 6.55 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
open-llama-7B-open-instruct.ggmlv3.q4_K_S.bin q4_K_S 4 3.79 GB 6.29 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
open-llama-7B-open-instruct.ggmlv3.q5_0.bin q5_0 5 4.63 GB 7.13 GB Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
open-llama-7B-open-instruct.ggmlv3.q5_1.bin q5_1 5 5.06 GB 7.56 GB Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
open-llama-7B-open-instruct.ggmlv3.q5_K_M.bin q5_K_M 5 4.77 GB 7.27 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
open-llama-7B-open-instruct.ggmlv3.q5_K_S.bin q5_K_S 5 4.63 GB 7.13 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
open-llama-7B-open-instruct.ggmlv3.q6_K.bin q6_K 6 5.53 GB 8.03 GB New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors
open-llama-7B-open-instruct.ggmlv3.q8_0.bin q8_0 8 7.16 GB 9.66 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 open-llama-7B-open-instruct.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.

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the 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.

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: VMware's open-llama-7B-open-instruct

VMware/open-llama-7B-open-instruct

Instruction-tuned version of the fully trained Open LLama 7B model. The model is open for COMMERCIAL USE.

NOTE : The model was trained using the Alpaca prompt template

License

Nomenclature

  • Model : Open-llama
  • Model Size: 7B parameters
  • Dataset: Open-instruct-v1 (oasst,dolly, hhrlhf)

Use in Transformers

import os
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = 'VMware/open-llama-7B-open-instruct'


tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype= torch.float16, device_map = 'sequential')

prompt_template = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"

prompt=  'Explain in simple terms how the attention mechanism of a transformer model works'


inputt = prompt_template.format(instruction= prompt)
input_ids = tokenizer(inputt, return_tensors="pt").input_ids.to("cuda")

output1 = model.generate(input_ids, max_length=512)
input_length = input_ids.shape[1]
output1 = output1[:, input_length:]
output= tokenizer.decode(output1[0])

print(output)

'''
 Attention is a mechanism used in deep learning models, such as transformer models, to capture global dependencies between different parts of the input. In a transformer model, the attention mechanism works by computing a weighted sum of the input vectors and then applying a non-linear activation function to the result.

The attention mechanism in a transformer model works in two steps:

1. Query-Key Mapping: First, the input sequence is divided into two parts: the query vector and the key vector. The query vector represents the input at the current position, and the key vector represents the input at a previous position.

2. Attention Weight Calculation: Second, the attention weights are calculated using the dot product between the query vector and each key vector. The attention weights represent the importance of the input at the previous position to the current position.

The attention weights are then used to compute the attention score for each input element. The attention score represents the relevance of the input element to the current position.

The attention mechanism in a transformer model is designed to capture global dependencies between different parts of the input. By attending to input elements from different positions, the model can learn to understand the relationships between different parts of the input. This allows the model to perform more complex tasks, such as understanding the relationships between words in a sentence or pixels in an image.</s>

'''

Finetuning details

The finetuning scripts will be available in our RAIL Github Repository

Evaluation

TODO