MetaLlama 3Open SourceMay 27, 2024

NousResearch: Hermes 2 Pro - Llama-3 8B

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.

Context Window
8K
tokens
Max Output
8K
tokens
Released
May 27, 2024
Arena Rank
—

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
⚡Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Repetition Penalty
Penalize repeated tokens
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
structured_outputs
Temperature
Controls randomness
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouter$0.14$0.14—
Martian$0.14$0.14—

Benchmarks

Open LLM Leaderboard
AverageOpen LLM Leaderboard
22.07/100
IFEvalOpen LLM Leaderboard
53.62/100
BBHOpen LLM Leaderboard
30.67/100
MATH Lvl 5Open LLM Leaderboard
8.38/100
GPQAOpen LLM Leaderboard
5.7/100
MUSROpen LLM Leaderboard
11.25/100
MMLU-PROOpen LLM Leaderboard
22.8/100

Model IDs

OpenRouternousresearch/hermes-2-pro-llama-3-8b
Hugging FaceNousResearch/Hermes-2-Pro-Llama-3-8B ↗
Compare with another model

Related Models

Meta#195

Meta: Llama 3 70B Instruct

8K ctx$0.51/1M in
Meta#225

Meta: Llama 3 8B Instruct

8K ctx$0.03/1M in
Meta#258

Meta: Llama 3.2 3B Instruct (free)

131K ctxFree/1M in
Meta#287

Meta: Llama 3.2 1B Instruct

60K ctx$0.03/1M in
Meta

Meta Llama 3 8B Instruct Lite

8K ctx$0.10/1M in
Meta

Llama 3.2 3B Instruct Turbo

131K ctx$0.06/1M in
← Back to all models