423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2026-01-12 09:00:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[release] Bye 2025 (#9702)

Browse Source
This commit is contained in:
Yaowei Zheng
2025-12-31 22:22:40 +08:00
committed by GitHub
parent 000526908a
commit 95ac3f2373
59 changed files with 154 additions and 401 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/ktransformers/infer_lora/deepseek2_lora_sft_kt.yaml Normal file
View File

@@ -0,0 +1,10 @@
model_name_or_path: deepseek-ai/DeepSeek-V2-Lite
adapter_name_or_path: saves/Kllama_deepseekV2
template: deepseek
infer_backend: ktransformers # choices: [huggingface, vllm, sglang, ktransformers]
trust_remote_code: true
use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V2-Lite-Chat-sft-amx.yaml
cpu_infer: 32
chunk_size: 8192

9
examples/ktransformers/infer_lora/deepseek3_kt.yaml Normal file
View File

@@ -0,0 +1,9 @@
model_name_or_path: opensourcerelease/DeepSeek-V3-bf16
template: deepseek
infer_backend: ktransformers # choices: [huggingface, vllm, sglang, ktransformers]
trust_remote_code: true
use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V3-Chat-sft-amx-multi-gpu.yaml
cpu_infer: 32
chunk_size: 8192

10
examples/ktransformers/infer_lora/deepseek3_lora_sft_kt.yaml Normal file
View File

@@ -0,0 +1,10 @@
model_name_or_path: opensourcerelease/DeepSeek-V3-bf16
adapter_name_or_path: saves/Kllama_deepseekV3
template: deepseek
infer_backend: ktransformers # choices: [huggingface, vllm, sglang, ktransformers]
trust_remote_code: true
use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V3-Chat-sft-amx-multi-gpu.yaml
cpu_infer: 32
chunk_size: 8192

10
examples/ktransformers/infer_lora/qwen3moe_lora_sft_kt.yaml Normal file
View File

@@ -0,0 +1,10 @@
model_name_or_path: Qwen/Qwen3-235B-A22B-Instruct-2507
adapter_name_or_path: saves/Kllama_Qwen3MoE_235bA22b
template: qwen3_nothink
infer_backend: ktransformers # choices: [huggingface, vllm, sglang, ktransformers]
trust_remote_code: true
use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/Qwen3Moe-sft-amx.yaml
cpu_infer: 32
chunk_size: 8192