Add commands to configs and update readme (#290)

* Add commands to configs and update readme

* update config

Author: daniellepintz

README.md

@@ -9,7 +9,7 @@ The primary purpose of the Forge ecosystem is to delineate infra concerns from m
 Key features:
 - Usability for rapid research (isolating the RL loop from infrastructure)
 - Hackability for power users (all parts of the RL loop can be easily modified without interacting with infrastructure)
-- Scalability (ability so shift between async and syncronous training and across thousands of GPUs)
+- Scalability (ability to shift between async and synchronous training and across thousands of GPUs)
 
 > ⚠️ **Early Development Warning** Forge is currently in an experimental
 > stage. You should expect bugs, incomplete features, and APIs that may change
@@ -47,7 +47,7 @@ Optional: By default, the packages installation uses conda. If user wants to ins
 After install, you can run the following command and should see output confirming GRPO training is running (you need a minimum 3 GPU devices):
 
 ```
-python -m apps.grpo.main  --config apps/grpo/qwen3_1_7b.yaml
+python -m apps.grpo.main --config apps/grpo/qwen3_1_7b.yaml
 ```
 
 If you need to re-build the wheels for whatever reason, you can do so with:

apps/grpo/qwen3_multinode.yaml

@@ -1,6 +1,7 @@
 # GRPO Training Configuration
 # Currently a fork of the main yaml, this just shows
 # placement of trainer and inference servers on separate hosts.
+# >>> python -m apps.grpo.main --config apps/grpo/qwen3_multinode.yaml
 
 # Global configuration
 group_size: 8

apps/vllm/deepseek_r1.yaml

@@ -1,3 +1,5 @@
+# >>> python -m apps.vllm.main --config apps/vllm/deepseek_r1.yaml
+
 # NOTE - this won't work until we have proper HostMesh support
 policy:
   engine_config:

apps/vllm/llama3_8b.yaml

@@ -1,3 +1,5 @@
+# >>> python -m apps.vllm.main --config apps/vllm/llama3_8b.yaml
+
 policy:
   engine_config:
     model: "meta-llama/Llama-3.1-8B-Instruct"

apps/vllm/qwen2_5_32b.yaml

@@ -1,3 +1,5 @@
+# >>> python -m apps.vllm.main --config apps/vllm/qwen2_5_32b.yaml
+
 policy:
   engine_config:
     model: "Qwen/Qwen2.5-32B"
@@ -12,7 +14,6 @@ policy:
 services:
   policy:
     procs: 4
-    hosts: 1
     num_replicas: 1
     with_gpus: true