[misc] support export ollama modelfile (#6899)

* support export ollama modelfile

* update config

* add system and num ctx

Former-commit-id: 8c2af7466f4015f300b51841db11bcd2505ebf20

examples/README.md

@@ -170,6 +170,12 @@ llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
 llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
 ```
 
+### Save Ollama modelfile
+
+```bash
+llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
+```
+
 ### Inferring LoRA Fine-Tuned Models
 
 #### Batch Generation using vLLM Tensor Parallel

examples/README_zh.md

@@ -170,6 +170,12 @@ llamafactory-cli export examples/merge_lora/llama3_lora_sft.yaml
 llamafactory-cli export examples/merge_lora/llama3_gptq.yaml
 ```
 
+### 保存 Ollama 配置文件
+
+```bash
+llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
+```
+
 ### 推理 LoRA 模型
 
 #### 使用 vLLM+TP 批量推理

examples/merge_lora/llama3_full_sft.yaml

@@ -0,0 +1,11 @@
+### model
+model_name_or_path: saves/llama3-8b/full/sft
+template: llama3
+trust_remote_code: true
+infer_dtype: bfloat16
+
+### export
+export_dir: output/llama3_full_sft
+export_size: 5
+export_device: cpu
+export_legacy_format: false

examples/merge_lora/llama3_gptq.yaml

@@ -4,9 +4,9 @@ template: llama3
 trust_remote_code: true
 
 ### export
-export_dir: models/llama3_gptq
+export_dir: output/llama3_gptq
 export_quantization_bit: 4
 export_quantization_dataset: data/c4_demo.json
-export_size: 2
+export_size: 5
 export_device: cpu
 export_legacy_format: false

examples/merge_lora/llama3_lora_sft.yaml

@@ -4,11 +4,10 @@
 model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
 adapter_name_or_path: saves/llama3-8b/lora/sft
 template: llama3
-finetuning_type: lora
 trust_remote_code: true
 
 ### export
-export_dir: models/llama3_lora_sft
-export_size: 2
+export_dir: output/llama3_lora_sft
+export_size: 5
 export_device: cpu
 export_legacy_format: false

examples/merge_lora/qwen2vl_lora_sft.yaml

@@ -4,11 +4,10 @@
 model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
 adapter_name_or_path: saves/qwen2_vl-7b/lora/sft
 template: qwen2_vl
-finetuning_type: lora
 trust_remote_code: true
 
 ### export
-export_dir: models/qwen2_vl_lora_sft
-export_size: 2
+export_dir: output/qwen2_vl_lora_sft
+export_size: 5
 export_device: cpu
 export_legacy_format: false