Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
hxssgaa
/
llama-3-8b-dpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
trl-lib/ultrafeedback_binarized
llama
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
207aa1d
llama-3-8b-dpo-full
/
generation_config.json
hxssgaa
Model save
207aa1d
verified
2 months ago
raw
Copy download link
history
blame
Safe
184 Bytes
{
"bos_token_id"
:
128000
,
"do_sample"
:
true
,
"eos_token_id"
:
[
128001
,
128008
,
128009
]
,
"temperature"
:
0.6
,
"top_p"
:
0.9
,
"transformers_version"
:
"4.45.1"
}