shibing624 / llama-3-8b-instruct-262k-chinese

huggingface.co
Total runs: 25
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: April 29 2024
text-generation

Introduction of llama-3-8b-instruct-262k-chinese

Model Details of llama-3-8b-instruct-262k-chinese

llama-3-8b-instruct-262k-chinese

llama-3-8b-instruct-262k-chinese基于 Llama-3-8B-Instruct-262k ,使用ORPO方法,在中英文偏好数据集 shibing624/DPO-En-Zh-20k-Preference 上微调得到的对话模型。

模型的部署、训练等方法详见MedicalGPT的GitHub仓库: https://github.com/shibing624/MedicalGPT

Relate models
Features

模型优势:

  1. 支持超长context length 262k token,适合RAG
  2. 支持中英文
  3. 支持多轮对话,代码编码、推理能力强,英文知识充分
  4. 模型推理需要显存:
Quantization Peak Usage for Encoding 2048 Tokens Peak Usage for Generating 8192 Tokens
FP16/BF16 18.66GB 24.58GB
Int4 9.21GB 14.62GB

缺点:

  1. model size只有8B,知识类问答幻觉明显
  2. 中文知识欠缺,容易幻觉,特别是中文古文知识,属于llama类模型通病
如何使用
import transformers
import torch

model_id = "shibing624/llama-3-8b-instruct-262k-chinese"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.float16},
    device="cuda",
)

messages = [{"role": "system", "content": ""}]
messages.append({"role": "user", "content": "介绍一下机器学习"})
prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
    )
terminators = [
        pipeline.tokenizer.eos_token_id,
        pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
    ]
outputs = pipeline(
    prompt,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9
)
content = outputs[0]["generated_text"][len(prompt):]
print(content)

result:

机器学习(Machine Learning)是一种基于计算机算法的自动数据分析技术,用于从数据中学习并预测未来的结果。它是人工智能(AI)和数据挖掘(Data Mining)的子领域,旨在通过训练和调整算法来发现数据中的模式、关系和规律。

机器学习算法可以分为监督学习、无监督学习和半监督学习三类:

1. 监督学习(Supervised Learning):在这种类型的学习中,算法被提供带有标签的数据集,用于训练。算法学习如何将输入数据映射到输出数据,并在新数据上进行预测。常见的监督学习算法包括逻辑回归、决策树、支持向量机(SVM)、随机森林和神经网络。
2. 无监督学习(Unsupervised Learning):在这种类型的学习中,算法没有标签数据。算法学习数据中的模式、结构和关系,并可能发现新的数据集群或特征。常见的无监督学习算法包括聚类、主成分分析(PCA)、独立成分分析(ICA)和高维度数据降维。
3. 半监督学习(Semi-supervised Learning):在这种类型的学习中,算法被提供部分带有标签的数据集。算法学习如何将输入数据映射到输出数据,并在新数据上进行预测。半监督学习算法结合了监督学习和无监督学习的优点,常见的半监督学习算法包括自我标注(Self-Labeling)和基于图的半监督学习(Graph-based Semi-supervised Learning)。

机器学习的应用广泛,包括自然语言处理、计算机视觉、推荐系统、人工智能和自动驾驶等领域。它的优势包括:

1. 自动化:机器学习算法可以自动从数据中发现模式和关系,无需人为干预。
2. 高效性:机器学习算法可以处理大量数据,并且可以在不需要人为干预的情况下进行预测。
3. 适应性:机器学习算法可以根据数据集的变化和更新进行调整。
4. 精准性:机器学习算法可以通过训练和测试来提高预测的准确性。
train detail

train loss:

eval loss:

About Llama-3-8B-Instruct-262k

Gradient incorporates your data to deploy autonomous assistants that power critical operations across your business. To learn more or collaborate on a custom model.

This model extends LLama-3 8B's context length from 8k to -> 160K, developed by Gradient, sponsored by compute from Crusoe Energy . It demonstrates that SOTA LLMs can learn to operate on long context with minimal training (< 200M tokens) by appropriately adjusting RoPE theta.

Approach:

  • meta-llama/Meta-Llama-3-8B-Instruct as the base
  • NTK-aware interpolation [1] to initialize an optimal schedule for RoPE theta, followed by a new data-driven RoPE theta optimization technique
  • Progressive training on increasing context lengths similar to the Large World Model [2] (See details below)

Infra:

We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 262144 tokens on Crusoe Energy high performance L40S cluster.

Data:

For training data, we generate long contexts by augmenting SlimPajama .

Progressive Training Details:

Parameter 65K 262K
Initialize From LLaMA-3-8B-Inst 65K
Sequence Length 2^16 2^18
RoPE theta 15.3 M 207.1 M
Batch Size (Tokens / Step) 2.097 M 4.192 M
Steps 30 24
Total Tokens 63 M 101 M
Learning Rate 2.00E-05 2.00E-05
# GPUs 32 32
GPU Type NVIDIA L40S NVIDIA L40S

Runs of shibing624 llama-3-8b-instruct-262k-chinese on huggingface.co

25
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About llama-3-8b-instruct-262k-chinese huggingface.co Model

More llama-3-8b-instruct-262k-chinese license Visit here:

https://choosealicense.com/licenses/llama3

llama-3-8b-instruct-262k-chinese huggingface.co

llama-3-8b-instruct-262k-chinese huggingface.co is an AI model on huggingface.co that provides llama-3-8b-instruct-262k-chinese's model effect (), which can be used instantly with this shibing624 llama-3-8b-instruct-262k-chinese model. huggingface.co supports a free trial of the llama-3-8b-instruct-262k-chinese model, and also provides paid use of the llama-3-8b-instruct-262k-chinese. Support call llama-3-8b-instruct-262k-chinese model through api, including Node.js, Python, http.

llama-3-8b-instruct-262k-chinese huggingface.co Url

https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese

shibing624 llama-3-8b-instruct-262k-chinese online free

llama-3-8b-instruct-262k-chinese huggingface.co is an online trial and call api platform, which integrates llama-3-8b-instruct-262k-chinese's modeling effects, including api services, and provides a free online trial of llama-3-8b-instruct-262k-chinese, you can try llama-3-8b-instruct-262k-chinese online for free by clicking the link below.

shibing624 llama-3-8b-instruct-262k-chinese online free url in huggingface.co:

https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese

llama-3-8b-instruct-262k-chinese install

llama-3-8b-instruct-262k-chinese is an open source model from GitHub that offers a free installation service, and any user can find llama-3-8b-instruct-262k-chinese on GitHub to install. At the same time, huggingface.co provides the effect of llama-3-8b-instruct-262k-chinese install, users can directly use llama-3-8b-instruct-262k-chinese installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama-3-8b-instruct-262k-chinese install url in huggingface.co:

https://huggingface.co/shibing624/llama-3-8b-instruct-262k-chinese

Url of llama-3-8b-instruct-262k-chinese

llama-3-8b-instruct-262k-chinese huggingface.co Url

Provider of llama-3-8b-instruct-262k-chinese huggingface.co

shibing624
ORGANIZATIONS

Other API from shibing624

huggingface.co

Total runs: 52
Run Growth: -74
Growth Rate: -151.02%
Updated: February 19 2024