DataLearner logo
LL

LLaMA2 70B

Foundation modelLLaMA2

Large Language Model Meta AI - 2 - 70B

Release date: 2023-07-18Updated: 2023-08-15 18:02:37.321738
Parameters
70B
Context length
4K
Chinese support
Not supported
Reasoning ability

Large Language Model Meta AI - 2 - 70B is an AI model published by Facebook AI Research Lab, released on 2023-07-18, for Foundation model, with 70B parameters, and 4K context length, requiring about 129GB storage, with a 87.00 score on HumanEval pass@100.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

LLaMA2 70B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
4K tokens
Max output length
No data
Model type
Foundation model
Modality (in / out)
No data
Release date
2023-07-18
Model file size
129GB
MoE architecture
No
Total params / Active params
70B / N/A
Knowledge cutoff
No data
LLaMA2 70B

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
No live demo
LLaMA2 70B

Official resources

Paper
DataLearnerAI blog
No blog post yet
LLaMA2 70B

API details

API speed
No data
No public API pricing yet.
LLaMA2 70B

Benchmark Results

LLaMA2 70B currently shows benchmark results led by AGIEval (6 / 28, score 54.20), GSM8K (38 / 70, score 56.80), MBPP pass@100 (8 / 13, score 83.10). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
68.90
77 / 124

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
56.80
38 / 70

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
45.40
54 / 70
HumanEval
Standard Mode
30.50
79 / 101

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
AGIEval
Standard Mode
54.20
6 / 28

Coding and Software Engineering

4 evaluations
Benchmark / mode
Score
Rank/total
HumanEval pass@100
Standard Mode
87
15 / 21
MBPP pass@100
Standard Mode
83.10
8 / 13
MBPP pass@10
Standard Mode
66.20
9 / 13
HumanEval pass@10
Standard Mode
59.40
13 / 18

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

LLaMA2 70B

Publisher

Facebook AI Research Lab
Facebook AI Research Lab
View publisher details
Large Language Model Meta AI - 2 - 70B

Model Overview

Large Language Model Meta AI - 2 - 70B is an AI model published by Facebook AI Research Lab, released on 2023-07-18, for Foundation model, with 70B parameters, and 4K context length, requiring about 129GB storage, with a 87.00 score on HumanEval pass@100.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code