update docs

Former-commit-id: a4a2e94241bea6f96590f6cb8ca8b5cddee1917e

examples/inference/api_demo.sh

@@ -1,7 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 API_PORT=8000 llamafactory-cli api \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora

examples/inference/cli_demo.sh

@@ -1,7 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 llamafactory-cli chat \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora

examples/inference/evaluate.sh

@@ -1,12 +0,0 @@
-#!/bin/bash
-
-CUDA_VISIBLE_DEVICES=0 llamafactory-cli eval \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template fewshot \
-    --finetuning_type lora \
-    --task mmlu \
-    --split test \
-    --lang en \
-    --n_shot 5 \
-    --batch_size 4

examples/inference/llama3.yaml

@@ -0,0 +1,2 @@
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3

examples/inference/llama3_lora_sft.yaml

@@ -0,0 +1,4 @@
+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

examples/inference/llama3_vllm.yaml

@@ -0,0 +1,4 @@
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3
+infer_backend: vllm
+vllm_enforce_eager: true

examples/inference/web_demo.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-# add `--visual_inputs True` to load MLLM
-
-CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat \
-    --model_name_or_path meta-llama/Llama-2-7b-hf \
-    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
-    --template default \
-    --finetuning_type lora