Key Specifications

Vendorother
Versiontigerbot-70b-chat
Release Date2023-08-22
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 71.7 % 2023-08-22 5-shot view
HUMANEVAL 36 pass@1 2023-08-22 view
GSM8K 51.1 % 2023-08-22 0-shot CoT view
MATH 15.4 % 2023-08-22 0-shot CoT view
BBH 51.9 % 2023-08-22 3-shot CoT view
GPQA 31.2 % 2023-08-22 0-shot view
IFEVAL 55.7 % 2023-08-22 prompt_strict view
ARC 87.9 % 2023-08-22 challenge view
MUSR 39.3 % 2023-08-22 0-shot view
WINOGRANDE 66.3 % 2023-08-22 0-shot view

Pricing

Tier Price Currency
Input$0.9 / MtokUSD
Output$0.9 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2023-08-22

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

TigerBot 70B Chat

Model Overview

TigerLab TigerBot 70B Chat 中文对话模型, 4K 上下文, 基于 Llama 2 微调, 中文场景优化。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other tigerbot-70b-chat 2023-08-22 4K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 71.7 % 5-shot
HumanEval 36.0 pass@1
GSM8K (Grade School Math 8K) 51.1 % 0-shot CoT
MATH 15.4 % 0-shot CoT
BBH (BIG-Bench Hard) 51.9 % 3-shot CoT
GPQA 31.2 % 0-shot
IFEval 55.7 % prompt_strict
ARC 87.9 % challenge
MUSR 39.3 % 0-shot
WinoGrande 66.3 % 0-shot

Pricing

Input Output Cache Read Cache Write

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • HumanEval 36.0, coding weak.
  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • General chat and Q&A

References