groupuser/Llama-3.2-1B-Instruct-finetuning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

삭제

Browse Source
This commit is contained in:
groupuser 2025-05-20 02:03:44 +00:00
parent 8fc301019e
commit d1273b5815
1 changed files with 0 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

89
config.pbtxt
View File

@ -1,89 +0,0 @@
# Triton backend to use
name: "Llama-3.2-1B-Instruct-finetuning"
backend: "python"
max_batch_size: 0
# Triton should expect as input a single string
# input of variable length named 'text_input'
input [
{
name: "text_input"
data_type: TYPE_STRING
dims: [ -1 ]
},
{
name: "max_length"
data_type: TYPE_INT32
dims: [ 1 ]
optional: true
},
{
name: "max_new_tokens"
data_type: TYPE_INT32
dims: [ 1 ]
optional: true
},
{
name: "do_sample"
data_type: TYPE_BOOL
dims: [ 1 ]
optional: true
},
{
name: "top_k"
data_type: TYPE_INT32
dims: [ 1 ]
optional: true
},
{
name: "top_p"
data_type: TYPE_FP32
dims: [ 1 ]
optional: true
},
{
name: "temperature"
data_type: TYPE_FP32
dims: [ 1 ]
optional: true
},
{
name: "repetition_penalty"
data_type: TYPE_FP32
dims: [ 1 ]
optional: true
},
{
name: "stream"
data_type: TYPE_BOOL
dims: [ 1 ]
optional: true
}
]
# Triton should expect to respond with a single string
# output of variable length named 'text_output'
output [
{
name: "text_output"
data_type: TYPE_STRING
dims: [ -1 ]
}
]
parameters: [
{
key: "enable_inference_trace",
value: {string_value: "True"}
}
]
instance_group [
{
kind: KIND_AUTO,
count: 1
}
]