Hugging Face's logo

RichardErkhov
/
juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf

GGUF
conversational
Model card Files
xet
 Community
How to use from
llama.cpp
Install (macOS, Linux) 
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
Install from WinGet (Windows) 
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
Use pre-built binary 
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
Build from source code 
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
Use Docker 
docker model run hf.co/RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf:
Quick Links

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Hermes-2-Theta-L3-Euryale-Ties-0.8-70B - GGUF

Name Quant method Size
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q2_K.gguf Q2_K 24.56GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_XS.gguf IQ3_XS 27.29GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_S.gguf IQ3_S 28.79GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_S.gguf Q3_K_S 28.79GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ3_M.gguf IQ3_M 29.74GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K.gguf Q3_K 31.91GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_M.gguf Q3_K_M 31.91GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q3_K_L.gguf Q3_K_L 34.59GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ4_XS.gguf IQ4_XS 35.64GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_0.gguf Q4_0 37.22GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.IQ4_NL.gguf IQ4_NL 37.58GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_K_S.gguf Q4_K_S 37.58GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_K.gguf Q4_K 39.6GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_K_M.gguf Q4_K_M 39.6GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q4_1.gguf Q4_1 41.27GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_0.gguf Q5_0 45.32GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_K_S.gguf Q5_K_S 45.32GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_K.gguf Q5_K 46.52GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_K_M.gguf Q5_K_M 46.52GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q5_1.gguf Q5_1 49.36GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q6_K.gguf Q6_K 53.91GB
Hermes-2-Theta-L3-Euryale-Ties-0.8-70B.Q8_0.gguf Q8_0 69.83GB

Original model description:

base_model:

  • Sao10K/L3-70B-Euryale-v2.1
  • NousResearch/Hermes-2-Theta-Llama-3-70B library_name: transformers tags:
  • mergekit
  • merge

Hermes-2-Theta-L3-Euryale-Ties-0.8-70B

This is a merge of pre-trained language models created using mergekit. I wanted to have enhanced roleplay performance and merged two of my favorite models together. I maybe release some merges like this with different methods and biases. This config seemed to be the best mix of both world on first glance. I will update my experiences further in the future.

Merge Details

Merge Method

This model was merged using the TIES merge method using NousResearch/Hermes-2-Theta-Llama-3-70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Hermes-2-Theta-Llama-3-70B
    parameters:
      weight: 0.8
  - model: Sao10K/L3-70B-Euryale-v2.1
    parameters:
      weight: 0.2
merge_method: ties
base_model: NousResearch/Hermes-2-Theta-Llama-3-70B
parameters:
  density: 0.7
  normalize: true
dtype: float16
tokenizer_source: base
Downloads last month
791
GGUF
Model size
71B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for RichardErkhov/juvi21_-_Hermes-2-Theta-L3-Euryale-Ties-0.8-70B-gguf