Hugging Face's logo

tensorblock
/
Hermes-3-Llama-3.1-70B-GGUF

GGUF
English
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Hermes-3-Llama-3.1-70B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
96c0c22 verified
preview code
|
raw
history blame
5.44 kB
metadata
language:
  - en
license: llama3
tags:
  - Llama-3
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - function calling
  - json mode
  - axolotl
  - roleplaying
  - chat
  - TensorBlock
  - GGUF
base_model: NousResearch/Hermes-3-Llama-3.1-70B
widget:
  - example_title: Hermes 3
    messages:
      - role: system
        content: >-
          You are a sentient, superintelligent artificial general intelligence,
          here to teach and assist me.
      - role: user
        content: What is the meaning of life?
model-index:
  - name: Hermes-3-Llama-3.1-70B
    results: []
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

NousResearch/Hermes-3-Llama-3.1-70B - GGUF

This repo contains GGUF format model files for NousResearch/Hermes-3-Llama-3.1-70B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template 

<|begin_of_text|><|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
Hermes-3-Llama-3.1-70B-Q2_K.gguf Q2_K 26.375 GB smallest, significant quality loss - not recommended for most purposes
Hermes-3-Llama-3.1-70B-Q3_K_S.gguf Q3_K_S 30.912 GB very small, high quality loss
Hermes-3-Llama-3.1-70B-Q3_K_M.gguf Q3_K_M 34.267 GB very small, high quality loss
Hermes-3-Llama-3.1-70B-Q3_K_L.gguf Q3_K_L 37.141 GB small, substantial quality loss
Hermes-3-Llama-3.1-70B-Q4_0.gguf Q4_0 39.970 GB legacy; small, very high quality loss - prefer using Q3_K_M
Hermes-3-Llama-3.1-70B-Q4_K_S.gguf Q4_K_S 40.347 GB small, greater quality loss
Hermes-3-Llama-3.1-70B-Q4_K_M.gguf Q4_K_M 42.520 GB medium, balanced quality - recommended
Hermes-3-Llama-3.1-70B-Q5_0.gguf Q5_0 48.657 GB legacy; medium, balanced quality - prefer using Q4_K_M
Hermes-3-Llama-3.1-70B-Q5_K_S.gguf Q5_K_S 48.657 GB large, low quality loss - recommended
Hermes-3-Llama-3.1-70B-Q5_K_M.gguf Q5_K_M 49.950 GB large, very low quality loss - recommended
Hermes-3-Llama-3.1-70B-Q6_K Q6_K 57.888 GB very large, extremely low quality loss
Hermes-3-Llama-3.1-70B-Q8_0 Q8_0 16.506 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Hermes-3-Llama-3.1-70B-GGUF --include "Hermes-3-Llama-3.1-70B-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Hermes-3-Llama-3.1-70B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'