[release] Bye 2025 (#9702)

examples/inference/deepseek2_lora_sft_kt.yaml

@@ -1,10 +0,0 @@
-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

examples/inference/deepseek3_kt.yaml

@@ -1,9 +0,0 @@
-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

examples/inference/deepseek3_lora_sft_kt.yaml

@@ -1,10 +0,0 @@
-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

examples/inference/llama3_lora_sft.yaml

@@ -1,5 +0,0 @@
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-adapter_name_or_path: saves/llama3-8b/lora/sft
-template: llama3
-infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
-trust_remote_code: true

examples/inference/qwen3.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
-template: qwen2_vl
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
+template: qwen3_nothink
 infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
 trust_remote_code: true

examples/inference/qwen3_full_sft.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: saves/llama3-8b/full/sft
-template: llama3
+model_name_or_path: saves/qwen3-4b/full/sft
+template: qwen3_nothink
 infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
 trust_remote_code: true

examples/inference/qwen3_lora_sft.yaml

@@ -0,0 +1,5 @@
+model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
+adapter_name_or_path: saves/qwen3-4b/lora/sft
+template: qwen3_nothink
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
+trust_remote_code: true

examples/inference/qwen3moe_lora_sft_kt.yaml

@@ -1,10 +0,0 @@
-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

examples/inference/qwen3vl.yaml

@@ -1,4 +1,4 @@
-model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
-template: llama3
+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
+template: qwen3_vl_nothink
 infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
 trust_remote_code: true