change doc

Author: NathanHB

docs/source/use-vllm-as-backend.mdx

@@ -29,20 +29,35 @@ lighteval vllm \
     "leaderboard|truthfulqa:mc|0|0"
 ```
 
-Available arguments for `vllm` can be found in the `VLLMModelConfig`:
-
-- **pretrained** (str): HuggingFace Hub model ID name or the path to a pre-trained model to load.
-- **gpu_memory_utilisation** (float): The fraction of GPU memory to use.
-- **revision** (str): The revision of the model.
-- **dtype** (str, None): The data type to use for the model.
-- **tensor_parallel_size** (int): The number of tensor parallel units to use.
-- **data_parallel_size** (int): The number of data parallel units to use.
-- **max_model_length** (int): The maximum length of the model.
-- **swap_space** (int): The CPU swap space size (GiB) per GPU.
-- **seed** (int): The seed to use for the model.
-- **trust_remote_code** (bool): Whether to trust remote code during model loading.
-- **add_special_tokens** (bool): Whether to add special tokens to the input sequences.
-- **multichoice_continuations_start_space** (bool): Whether to add a space at the start of each continuation in multichoice generation.
+For more advanced configurations, you can use a config file for the model.
+An example of a config file is shown below and can be found at `examples/model_configs/vllm_model_config.yaml`.
+
+```bash
+lighteval vllm \
+    "examples/model_configs/vllm_model_config.yaml" \
+    "leaderboard|truthfulqa:mc|0|0"
+```
+
+```yaml
+model: # Model specific parameters
+  base_params:
+    model_args: "pretrained=HuggingFaceTB/SmolLM-1.7B,revision=main,dtype=bfloat16" # Model args that you would pass in the command line
+  generation: # Generation specific parameters
+    temperature: 0.3
+    early_stopping: 1
+    repetition_penalty: 1.0
+    frequency_penalty: 0.0
+    length_penalty: 0.0
+    presence_penalty: 0.0
+    max_new_tokens: 100
+    min_new_tokens: 1
+    seed: 42
+    stop_tokens: null
+    top_k: 0
+    min_p: 0.0
+    top_p: 0.9
+    truncate_prompt: false
+```
 
 > [!WARNING]
 > In the case of OOM issues, you might need to reduce the context size of the