metadata
datasets:
- argilla/ultrafeedback-binarized-preferences
language:
- en
base_model: argilla/notus-7b-v1
library_name: transformers
pipeline_tag: text-generation
tags:
- dpo
- rlaif
- preference
- ultrafeedback
- TensorBlock
- GGUF
license: mit
model-index:
- name: notus-7b-v1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 0.6459044368600683
name: normalized accuracy
source:
url: >-
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
name: Open LLM Leaderboard Results
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 0.8478390758812986
name: normalized accuracy
source:
url: >-
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
name: Open LLM Leaderboard Results
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 0.5436768358952805
source:
url: >-
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
name: Open LLM Leaderboard Results
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 0.6303308230938872
name: accuracy
source:
url: >-
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
name: Open LLM Leaderboard Results
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 0.1516300227445034
name: accuracy
source:
url: >-
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
name: Open LLM Leaderboard Results
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 0.7940015785319653
name: accuracy
source:
url: >-
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/argilla/notus-7b-v1/results_2023-11-29T22-16-51.521321.json
name: Open LLM Leaderboard Results
- task:
type: text-generation
name: Text Generation
dataset:
name: AlpacaEval
type: tatsu-lab/alpaca_eval
metrics:
- type: tatsu-lab/alpaca_eval
value: 0.9142
name: win rate
source:
url: https://tatsu-lab.github.io/alpaca_eval/
- task:
type: text-generation
name: Text Generation
dataset:
name: MT-Bench
type: unknown
metrics:
- type: unknown
value: 7.3
name: score
source:
url: https://huggingface.co/spaces/lmsys/mt-bench
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
argilla/notus-7b-v1 - GGUF
This repo contains GGUF format model files for argilla/notus-7b-v1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|system|>
{system_prompt}</s>
<|user|>
{prompt}</s>
<|assistant|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| notus-7b-v1-Q2_K.gguf | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
| notus-7b-v1-Q3_K_S.gguf | Q3_K_S | 2.947 GB | very small, high quality loss |
| notus-7b-v1-Q3_K_M.gguf | Q3_K_M | 3.277 GB | very small, high quality loss |
| notus-7b-v1-Q3_K_L.gguf | Q3_K_L | 3.560 GB | small, substantial quality loss |
| notus-7b-v1-Q4_0.gguf | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| notus-7b-v1-Q4_K_S.gguf | Q4_K_S | 3.856 GB | small, greater quality loss |
| notus-7b-v1-Q4_K_M.gguf | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
| notus-7b-v1-Q5_0.gguf | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| notus-7b-v1-Q5_K_S.gguf | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
| notus-7b-v1-Q5_K_M.gguf | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
| notus-7b-v1-Q6_K.gguf | Q6_K | 5.534 GB | very large, extremely low quality loss |
| notus-7b-v1-Q8_0.gguf | Q8_0 | 7.167 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/notus-7b-v1-GGUF --include "notus-7b-v1-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/notus-7b-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'