ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add trust_remote_code defaults to all model configs

Browse source
This commit is contained in:
Roland Tannous 2026-03-09 09:54:52 +00:00
commit cb741f8232
65 changed files with 154 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

2
studio/backend/assets/configs/model_defaults/default.yaml
View file

@ -2,6 +2,7 @@
# Used for models without specific configurations
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -47,6 +48,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.7
top_p: 0.95
top_k: -1

3
studio/backend/assets/configs/model_defaults/ernie/unsloth_ERNIE-4.5-21B-A3B-PT.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/ERNIE-4.5-21B-A3B-PT
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/ernie/unsloth_ERNIE-4.5-VL-28B-A3B-PT.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: true
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -48,6 +49,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: true
temperature: 1.5
min_p: 0.1

3
studio/backend/assets/configs/model_defaults/falcon/tiiuae_Falcon-H1-0.5B-Instruct.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: tiiuae/Falcon-H1-0.5B-Instruct, unsloth/Falcon-H1-0.5B-Instruct
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_codegemma-7b-bnb-4bit.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from Ollama
training:
trust_remote_code: false
max_seq_length: 4096
# num_epochs: 4
num_epochs: 0
@ -44,5 +45,6 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0
top_p: 0.9

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_functiongemma-270m-it.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 4096
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

3
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-2-27b-bnb-4bit.yaml
View file

@ -2,6 +2,7 @@
# Based on Gemma2_(9B)-Alpaca.ipynb (same defaults for larger models)
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -41,3 +42,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-2-2b.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/gemma-2-2b-bnb-4bit, google/gemma-2-2b
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-270m-it.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-27b-it.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-4b-it.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3-4b-pt.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 2
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3n-E4B-it.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 1024
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
audio_input: true
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/gemma/unsloth_gemma-3n-E4B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 2
num_epochs: 0
@ -44,6 +45,7 @@ logging:
audio_input: true
inference:
trust_remote_code: false
temperature: 1.0
top_k: 64
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/gpt-oss/unsloth_gpt-oss-120b.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 4096
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_p: 1.0
top_k: 0

2
studio/backend/assets/configs/model_defaults/gpt-oss/unsloth_gpt-oss-20b.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 1024
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.0
top_p: 1.0
top_k: 0

2
studio/backend/assets/configs/model_defaults/granite/unsloth_granite-4.0-350m-unsloth-bnb-4bit.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -46,6 +47,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.0
top_p: 1.0
top_k: 0

2
studio/backend/assets/configs/model_defaults/granite/unsloth_granite-4.0-h-micro.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -46,6 +47,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.0
top_p: 1.0
top_k: 0

2
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.2-11B-Vision-Instruct.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

3
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.2-1B-Instruct.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit, meta-llama/Llama-3.2-1B-Instruct, unsloth/Llama-3.2-1B-Instruct-bnb-4bit, RedHatAI/Llama-3.2-1B-Instruct-FP8, unsloth/Llama-3.2-1B-Instruct-FP8-Block, unsloth/Llama-3.2-1B-Instruct-FP8-Dynamic
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 5
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.2-3B-Instruct.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

2
studio/backend/assets/configs/model_defaults/llama/unsloth_Llama-3.3-70B-Instruct.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

3
studio/backend/assets/configs/model_defaults/llama/unsloth_Meta-Llama-3.1-70B-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Meta-Llama-3.1-8B-bnb-4bit, unsloth/Meta-Llama-3.1-8B-unsloth-bnb-4bit, meta-llama/Meta-Llama-3.1-8B, unsloth/Meta-Llama-3.1-8B, unsloth/Meta-Llama-3.1-70B, meta-llama/Meta-Llama-3.1-70B, unsloth/Meta-Llama-3.1-405B-bnb-4bit, meta-llama/Meta-Llama-3.1-405B
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

4
studio/backend/assets/configs/model_defaults/llama/unsloth_Meta-Llama-3.1-8B-Instruct-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: "unsloth/Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bit", "meta-llama/Meta-Llama-3.1-8B-Instruct", "unsloth/Meta-Llama-3.1-8B-Instruct","RedHatAI/Llama-3.1-8B-Instruct-FP8","unsloth/Llama-3.1-8B-Instruct-FP8-Block","unsloth/Llama-3.1-8B-Instruct-FP8-Dynamic"
training:
trust_remote_code: false
max_seq_length: 8192
# num_epochs: 4
num_epochs: 0
@ -42,4 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/llama/unsloth_llama-3-8b-Instruct-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/llama-3-8b-Instruct, meta-llama/Meta-Llama-3-8B-Instruct
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/llama/unsloth_llama-3-8b-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/llama-3-8b, meta-llama/Meta-Llama-3-8B
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/llasa/unsloth_Llasa-3B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -39,6 +40,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.2
top_p: 1.2

2
studio/backend/assets/configs/model_defaults/mistral/unsloth_Magistral-Small-2509-unsloth-bnb-4bit.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -48,6 +49,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.7
min_p: 0.01
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/mistral/unsloth_Ministral-3-3B-Instruct-2512.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -48,6 +49,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.15
top_p: default

4
studio/backend/assets/configs/model_defaults/mistral/unsloth_Mistral-Nemo-Base-2407-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: "unsloth/Mistral-Nemo-Base-2407", "mistralai/Mistral-Nemo-Base-2407", "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit", "unsloth/Mistral-Nemo-Instruct-2407", "mistralai/Mistral-Nemo-Instruct-2407",
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,4 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/mistral/unsloth_Mistral-Small-Instruct-2409.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Mistral-Small-Instruct-2409-bnb-4bit, mistralai/Mistral-Small-Instruct-2409
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/mistral/unsloth_Pixtral-12B-2409.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

4
studio/backend/assets/configs/model_defaults/mistral/unsloth_mistral-7b-instruct-v0.3-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/mistral-7b-instruct-v0.3, mistralai/Mistral-7B-Instruct-v0.3
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,4 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

4
studio/backend/assets/configs/model_defaults/mistral/unsloth_mistral-7b-v0.3-bnb-4bit.yaml
View file

@ -2,6 +2,7 @@
# Based on Mistral_v0.3_(7B)-Alpaca.ipynb
# Also applies to: "unsloth/mistral-7b-v0.3", "mistralai/Mistral-7B-v0.3",
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -41,4 +42,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/other/OuteAI_Llama-OuteTTS-1.0-1B.yaml
View file

@ -6,6 +6,7 @@
audio_type: dac
training:
trust_remote_code: false
eval_steps: 0
max_seq_length: 2048
# num_epochs: 4
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.4
top_k: 40
top_p: 0.9

2
studio/backend/assets/configs/model_defaults/other/Spark-TTS-0.5B_LLM.yaml
View file

@ -6,6 +6,7 @@
audio_type: bicodec
training:
trust_remote_code: false
eval_steps: 0
max_seq_length: 2048
# num_epochs: 4
@ -47,6 +48,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.8
top_k: 50
top_p: 1.0

3
studio/backend/assets/configs/model_defaults/other/sesame_csm-1b.yaml
View file

@ -5,6 +5,7 @@
audio_type: csm
training:
trust_remote_code: false
eval_steps: 0
max_seq_length: 2048
# num_epochs: 4
@ -45,3 +46,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/other/unsloth_GLM-4.7-Flash.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/GLM-4.7-Flash-unsloth-bnb-4bit, unsloth/GLM-4.7-Flash-bnb-4bit, THUDM/GLM-4.7-Flash
training:
trust_remote_code: true
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: true
temperature: 0.7
top_p: 0.8
top_k: 20

2
studio/backend/assets/configs/model_defaults/other/unsloth_LFM2-1.2B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -38,6 +39,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.3
min_p: 0.15

2
studio/backend/assets/configs/model_defaults/other/unsloth_Nemotron-3-Nano-30B-A3B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: true
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -46,6 +47,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: true
temperature: 1.0
top_p: 1.0

2
studio/backend/assets/configs/model_defaults/other/unsloth_PaddleOCR-VL.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: true
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -48,6 +49,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: true
temperature: 1.5
min_p: 0.1

3
studio/backend/assets/configs/model_defaults/other/unsloth_answerdotai_ModernBERT-large.yaml
View file

@ -2,6 +2,7 @@
# Based on bert_classification.ipynb
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 1
num_epochs: 0
@ -41,3 +42,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/other/unsloth_orpheus-3b-0.1-ft.yaml
View file

@ -6,6 +6,7 @@
audio_type: snac
training:
trust_remote_code: false
eval_steps: 0
max_seq_length: 2048
# num_epochs: 4
@ -47,6 +48,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_p: 0.95

3
studio/backend/assets/configs/model_defaults/other/unsloth_tinyllama-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
training:
trust_remote_code: false
max_seq_length: 4096
# num_epochs: 1
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/other/unsloth_whisper-large-v3.yaml
View file

@ -6,6 +6,7 @@ audio_type: whisper
audio_input: true
training:
trust_remote_code: false
eval_steps: 5
max_seq_length: 448
# num_epochs: 4
@ -41,3 +42,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

4
studio/backend/assets/configs/model_defaults/phi/unsloth_Phi-3-medium-4k-instruct.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: "unsloth/Phi-3-medium-4k-instruct-bnb-4bit", "microsoft/Phi-3-medium-4k-instruct",
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,4 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

4
studio/backend/assets/configs/model_defaults/phi/unsloth_Phi-3.5-mini-instruct.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: "unsloth/Phi-3.5-mini-instruct-bnb-4bit", "microsoft/Phi-3.5-mini-instruct"
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,4 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/phi/unsloth_Phi-4.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.8
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/qwen/imdatta0_tiny_qwen3_moe_2.8B_0.7B.yaml
View file

@ -4,6 +4,7 @@
# MoE model - includes gate_up_proj for MoE layers
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -45,6 +46,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_k: 20
top_p: 0.95

3
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2-7B.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Qwen2-7B-bnb-4bit, Qwen/Qwen2-7B
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2-VL-7B-Instruct.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

3
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-1.5B-Instruct.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Qwen2.5-1.5B-Instruct-unsloth-bnb-4bit, Qwen/Qwen2.5-1.5B-Instruct, unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
training:
trust_remote_code: false
max_seq_length: 4096
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-7B.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Qwen2.5-7B-unsloth-bnb-4bit, Qwen/Qwen2.5-7B, unsloth/Qwen2.5-7B-bnb-4bit
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

3
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-Coder-1.5B-Instruct.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit, Qwen/Qwen2.5-Coder-1.5B-Instruct
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-Coder-14B-Instruct.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

3
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-Coder-7B-Instruct-bnb-4bit.yaml
View file

@ -3,6 +3,7 @@
# Also applies to: unsloth/Qwen2.5-Coder-7B-Instruct, Qwen/Qwen2.5-Coder-7B-Instruct
training:
trust_remote_code: false
max_seq_length: 32768
# num_epochs: 4
num_epochs: 0
@ -42,3 +43,5 @@ logging:
tensorboard_dir: "runs"
log_frequency: 10
inference:
trust_remote_code: false

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen2.5-VL-7B-Instruct-bnb-4bit.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth notebook
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 1.5
min_p: 0.1

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-0.6B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from Ollama
training:
trust_remote_code: false
max_seq_length: 1024
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_k: 20
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-14B-Base-unsloth-bnb-4bit.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from Ollama
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_k: 20
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-14B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from Ollama
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_k: 20
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-30B-A3B-Instruct-2507.yaml
View file

@ -4,6 +4,7 @@
# MoE model - includes gate_up_proj for MoE layers
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -45,6 +46,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_k: 20
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-32B.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from Ollama
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_k: 20
top_p: 0.95

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-4B-Instruct-2507.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.7
top_p: 0.80
top_k: 20

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-4B-Thinking-2507.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -44,6 +45,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.6
top_p: 0.95
top_k: 20

2
studio/backend/assets/configs/model_defaults/qwen/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit.yaml
View file

@ -4,6 +4,7 @@
# added inference parameters from unsloth guides
training:
trust_remote_code: false
max_seq_length: 2048
# num_epochs: 4
num_epochs: 0
@ -42,6 +43,7 @@ logging:
log_frequency: 10
inference:
trust_remote_code: false
temperature: 0.7
top_p: 0.8
top_k: 20