Hugging Face's logo

tensorblock
/
Nous-Hermes-2-Yi-34B-GGUF

GGUF
English
yi
instruct
finetune
chatml
gpt4
synthetic data
distillation
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Nous-Hermes-2-Yi-34B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
a6110e6 verified
preview code
|
raw
history blame contribute delete
5.09 kB
metadata
base_model: NousResearch/Nous-Hermes-2-Yi-34B
tags:
  - yi
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - TensorBlock
  - GGUF
license: apache-2.0
language:
  - en
datasets:
  - teknium/OpenHermes-2.5
model-index:
  - name: Nous-Hermes-2-Yi-34B
    results: []
TensorBlock

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

NousResearch/Nous-Hermes-2-Yi-34B - GGUF

This repo contains GGUF format model files for NousResearch/Nous-Hermes-2-Yi-34B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template 

<|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
Nous-Hermes-2-Yi-34B-Q2_K.gguf Q2_K 11.944 GB smallest, significant quality loss - not recommended for most purposes
Nous-Hermes-2-Yi-34B-Q3_K_S.gguf Q3_K_S 13.933 GB very small, high quality loss
Nous-Hermes-2-Yi-34B-Q3_K_M.gguf Q3_K_M 15.511 GB very small, high quality loss
Nous-Hermes-2-Yi-34B-Q3_K_L.gguf Q3_K_L 16.894 GB small, substantial quality loss
Nous-Hermes-2-Yi-34B-Q4_0.gguf Q4_0 18.130 GB legacy; small, very high quality loss - prefer using Q3_K_M
Nous-Hermes-2-Yi-34B-Q4_K_S.gguf Q4_K_S 18.253 GB small, greater quality loss
Nous-Hermes-2-Yi-34B-Q4_K_M.gguf Q4_K_M 19.240 GB medium, balanced quality - recommended
Nous-Hermes-2-Yi-34B-Q5_0.gguf Q5_0 22.080 GB legacy; medium, balanced quality - prefer using Q4_K_M
Nous-Hermes-2-Yi-34B-Q5_K_S.gguf Q5_K_S 22.080 GB large, low quality loss - recommended
Nous-Hermes-2-Yi-34B-Q5_K_M.gguf Q5_K_M 22.651 GB large, very low quality loss - recommended
Nous-Hermes-2-Yi-34B-Q6_K.gguf Q6_K 26.276 GB very large, extremely low quality loss
Nous-Hermes-2-Yi-34B-Q8_0.gguf Q8_0 34.033 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/Nous-Hermes-2-Yi-34B-GGUF --include "Nous-Hermes-2-Yi-34B-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/Nous-Hermes-2-Yi-34B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'