Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ZhangShenao_-_SELM-Llama-3-8B-Instruct-iter-2-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
ZhangShenao_-_SELM-Llama-3-8B-Instruct-iter-2-gguf
like
0
2405.19332
conversational
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
SELM-Llama-3-8B-Instruct-iter-2 - GGUF
Model creator:
https://huggingface.co/ZhangShenao/
Original model:
https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-2/
Name
Quant method
Size
SELM-Llama-3-8B-Instruct-iter-2.Q2_K.gguf
Q2_K
2.96GB
SELM-Llama-3-8B-Instruct-iter-2.IQ3_XS.gguf
IQ3_XS
3.28GB
SELM-Llama-3-8B-Instruct-iter-2.IQ3_S.gguf
IQ3_S
3.43GB
SELM-Llama-3-8B-Instruct-iter-2.Q3_K_S.gguf
Q3_K_S
3.41GB
SELM-Llama-3-8B-Instruct-iter-2.IQ3_M.gguf
IQ3_M
3.52GB
SELM-Llama-3-8B-Instruct-iter-2.Q3_K.gguf
Q3_K
3.74GB
SELM-Llama-3-8B-Instruct-iter-2.Q3_K_M.gguf
Q3_K_M
3.74GB
SELM-Llama-3-8B-Instruct-iter-2.Q3_K_L.gguf
Q3_K_L
4.03GB
SELM-Llama-3-8B-Instruct-iter-2.IQ4_XS.gguf
IQ4_XS
4.18GB
SELM-Llama-3-8B-Instruct-iter-2.Q4_0.gguf
Q4_0
4.34GB
SELM-Llama-3-8B-Instruct-iter-2.IQ4_NL.gguf
IQ4_NL
4.38GB
SELM-Llama-3-8B-Instruct-iter-2.Q4_K_S.gguf
Q4_K_S
4.37GB
SELM-Llama-3-8B-Instruct-iter-2.Q4_K.gguf
Q4_K
4.58GB
SELM-Llama-3-8B-Instruct-iter-2.Q4_K_M.gguf
Q4_K_M
4.58GB
SELM-Llama-3-8B-Instruct-iter-2.Q4_1.gguf
Q4_1
4.78GB
SELM-Llama-3-8B-Instruct-iter-2.Q5_0.gguf
Q5_0
5.21GB
SELM-Llama-3-8B-Instruct-iter-2.Q5_K_S.gguf
Q5_K_S
5.21GB
SELM-Llama-3-8B-Instruct-iter-2.Q5_K.gguf
Q5_K
5.34GB
SELM-Llama-3-8B-Instruct-iter-2.Q5_K_M.gguf
Q5_K_M
5.34GB
SELM-Llama-3-8B-Instruct-iter-2.Q5_1.gguf
Q5_1
5.65GB
SELM-Llama-3-8B-Instruct-iter-2.Q6_K.gguf
Q6_K
6.14GB
SELM-Llama-3-8B-Instruct-iter-2.Q8_0.gguf
Q8_0
7.95GB
Original model description:
license: mit base_model: ZhangShenao/SELM-Llama-3-8B-Instruct-iter-1 tags:
alignment-handbook
dpo
trl
selm datasets:
HuggingFaceH4/ultrafeedback_binarized model-index:
name: SELM-Llama-3-8B-Instruct-iter-2 results: []
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
.
SELM-Llama-3-8B-Instruct-iter-2
This model is a fine-tuned version of
ZhangShenao/SELM-Llama-3-8B-Instruct-iter-1
using synthetic data based on on the HuggingFaceH4/ultrafeedback_binarized dataset.
Model description
Model type: A 8B parameter Llama3-instruct-based Self-Exploring Language Models (SELM).
License: MIT
Results
AlpacaEval 2.0 (LC WR)
MT-Bench (Average)
SELM-Llama-3-8B-Instruct-iter-3
33.47
8.29
SELM-Llama-3-8B-Instruct-iter-2
35.65
8.09
SELM-Llama-3-8B-Instruct-iter-1
32.02
7.92
Meta-Llama-3-8B-Instruct
24.31
7.93
Training hyperparameters
The following hyperparameters were used during training:
alpha: 0.0001
beta: 0.01
train_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
num_epochs: 1
Framework versions
Transformers 4.40.2
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.19.1
