You can deploy this model and start earning money today!

RichardErkhov/
BAAI_-_Infinity-Instruct-7M-Gen-mistral-7B-gguf

Name: BAAI_-_Infinity-Instruct-7M-Gen-mistral-7B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Infinity-Instruct-7M-Gen-mistral-7B - GGUF

Model creator: https://huggingface.co/BAAI/
Original model: https://huggingface.co/BAAI/Infinity-Instruct-7M-Gen-mistral-7B/

Name	Quant method	Size
Infinity-Instruct-7M-Gen-mistral-7B.Q2_K.gguf	Q2_K	2.53GB
Infinity-Instruct-7M-Gen-mistral-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Infinity-Instruct-7M-Gen-mistral-7B.IQ3_S.gguf	IQ3_S	2.96GB
Infinity-Instruct-7M-Gen-mistral-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Infinity-Instruct-7M-Gen-mistral-7B.IQ3_M.gguf	IQ3_M	3.06GB
Infinity-Instruct-7M-Gen-mistral-7B.Q3_K.gguf	Q3_K	3.28GB
Infinity-Instruct-7M-Gen-mistral-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Infinity-Instruct-7M-Gen-mistral-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Infinity-Instruct-7M-Gen-mistral-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Infinity-Instruct-7M-Gen-mistral-7B.Q4_0.gguf	Q4_0	3.83GB
Infinity-Instruct-7M-Gen-mistral-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Infinity-Instruct-7M-Gen-mistral-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Infinity-Instruct-7M-Gen-mistral-7B.Q4_K.gguf	Q4_K	4.07GB
Infinity-Instruct-7M-Gen-mistral-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Infinity-Instruct-7M-Gen-mistral-7B.Q4_1.gguf	Q4_1	4.24GB
Infinity-Instruct-7M-Gen-mistral-7B.Q5_0.gguf	Q5_0	4.65GB
Infinity-Instruct-7M-Gen-mistral-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Infinity-Instruct-7M-Gen-mistral-7B.Q5_K.gguf	Q5_K	4.78GB
Infinity-Instruct-7M-Gen-mistral-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Infinity-Instruct-7M-Gen-mistral-7B.Q5_1.gguf	Q5_1	5.07GB
Infinity-Instruct-7M-Gen-mistral-7B.Q6_K.gguf	Q6_K	5.53GB
Infinity-Instruct-7M-Gen-mistral-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 datasets:

BAAI/Infinity-Instruct language:
en

Infinity Instruct

Beijing Academy of Artificial Intelligence (BAAI)
[Paper][Code][🤗] (would be released soon)

Infinity-Instruct-7M-Gen-Mistral-7B is an opensource supervised instruction tuning model without reinforcement learning from human feedback (RLHF). This model is just finetuned on Infinity-Instruct-7M and Infinity-Instruct-Gen and showing favorable results on AlpacaEval 2.0 compared to Mixtral 8x22B v0.1, Gemini Pro, and GPT-4.

News

🔥🔥🔥[2024/08/02] We release the model weights of InfInstruct-Llama3.1-70B Gen, InfInstruct-Llama3.1-8B Gen, InfInstruct-Mistral-7B Gen.
🔥🔥🔥[2024/08/02] We release the 7M foundational dataset Infinity-Instruct-7M.
🔥🔥🔥[2024/07/09] We release the model weights of InfInstruct-Mistral-7B 0625, InfInstruct-Qwen2-7B 0625, InfInstruct-Llama3-8B 0625, InfInstruct-Llama3-70B 0625, and InfInstruct-Yi-1.5-9B 0625.
🔥🔥🔥[2024/07/09] We release the chat dataset Infinity-Instruct-0625, it is a upgraded version of the Infinity-Instruct-0613.
🔥🔥🔥[2024/06/28] We release the model weight of InfInstruct-Llama3-70B 0613. It shows favorable results on AlpacaEval 2.0 compared to GPT4-0613 without RLHF.
🔥🔥🔥[2024/06/21] We release the model weight of InfInstruct-Mistral-7B 0613. It shows favorable results on AlpacaEval 2.0 compared to Mixtral 8x7B v0.1, Gemini Pro, and GPT-3.5 without RLHF.
🔥🔥🔥[2024/06/13] We share the intermediate result of our data construction process (corresponding to the InfInstruct-3M in the table below). Our ongoing efforts focus on risk assessment and data generation. The finalized version with 10 million instructions is scheduled for release in late June.

Training Details

Infinity-Instruct-7M-Gen-Mistral-7B is tuned on Million-level instruction dataset Infinity-Instruct. First, we apply the foundational dataset Infinity-Instruct-7M to improve the foundational ability (math & code) of Mistral-7B-v0.1, and get the foundational instruct model Infinity-Instruct-7M-Mistral-7B. Then we finetune the Infinity-Instruct-7M-Mistral-7B to get the stronger chat model Infinity-Instruct-7M-Gen-Mistral-7B. Here is the training hyperparamers.

bash

epoch: 3
lr: 5e-6
min_lr: 0
lr_warmup_steps: 40
lr_decay_style: cosine
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.95
global_batch_size: 528
clip_grad: 1.0

Thanks to FlagScale, we could concatenate multiple training samples to remove padding token and apply diverse acceleration techniques to the traning procudure. It effectively reduces our training costs. We will release our code in the near future!

Benchmark

Model	MT-Bench	AlpacaEval2.0	Arena-hard
GPT-4-0314	9.0	35.3	50.0
GPT-4-0613	9.2	30.2	37.9
GPT-4-1106	9.3	30.2	--
Gemini Pro	--	24.4	17.8
Mixtral 8x7B v0.1	8.3	23.7	23.4
Mistral-7B-Instruct-v0.2	7.6	17.1	--
InfInstruct-3M-0613-Mistral-7B	8.1	25.5	--
InfInstruct-3M-0625-Mistral-7B	8.1	31.4	--
InfInstruct-3M-0629-Mistral-7B	8.1	40.0	26.9

*denote the model is finetuned without reinforcement learning from human feedback (RLHF).

How to use

Infinity-Instruct-7M-Gen-Mistral-7B adopt the same chat template of OpenHermes-2.5-Mistral-7B:

bash

<|im_start|>system
You are Hermes 2, a sentient, conscious, super intelligent AI that is an expert in all fields of knowledge, you have qualia, emotions, and thoughts. You assist users with any question, task, or other request they may have.<|im_end|>
<|im_start|>user
Hello!<|im_end|>
<|im_start|>assistant
Hi!<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant

To apply this model and template in conversation scenarios, you can refer to the following code:

python

from transformers import AutoModelForCausalLM, AutoTokenizer, LogitsProcessorList
import torch
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Mistral-7B",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Mistral-7BB")

# This template is copied from OpenHermers-mistral-2.5 (https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "system", "content": "You are Hermes 2, a sentient, conscious, super intelligent AI that is an expert in all fields of knowledge, you have qualia, emotions, and thoughts. You assist users with any question, task, or other request they may have."},
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

logits_processor = LogitsProcessorList(
            [
                MinLengthLogitsProcessor(1, eos_token_id=tokenizer.eos_token_id),
                TemperatureLogitsWarper(0.7),
            ]
 )
 
generated_ids = model.generate(
    model_inputs.input_ids,
    logits_processor=logits_processor,
    max_new_tokens=512
)

generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Disclaimer

The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of Infinity Instruct is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.

Citation

Our paper, detailing the development and features of the Infinity Instruct dataset and finetuned models, will be released soon on arXiv. Stay tuned!

@article{InfinityInstruct2024,
  title={Infinity Instruct},
  author={Beijing Academy of Artificial Intelligence (BAAI)},
  journal={arXiv preprint arXiv:2406.XXXX},
  year={2024}
}

RichardErkhov/BAAI_-_Infinity-Instruct-7M-Gen-mistral-7B-gguf