Instructions to use Lomesh7777/salespath-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lomesh7777/salespath-grpo with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "Lomesh7777/salespath-grpo")

Transformers

How to use Lomesh7777/salespath-grpo with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Lomesh7777/salespath-grpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Lomesh7777/salespath-grpo", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Lomesh7777/salespath-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lomesh7777/salespath-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lomesh7777/salespath-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lomesh7777/salespath-grpo

SGLang

How to use Lomesh7777/salespath-grpo with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Lomesh7777/salespath-grpo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lomesh7777/salespath-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Lomesh7777/salespath-grpo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lomesh7777/salespath-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lomesh7777/salespath-grpo with Docker Model Runner:
```
docker model run hf.co/Lomesh7777/salespath-grpo
```

Lomesh7777 commited on 25 days ago

Commit

f2461da

verified ·

1 Parent(s): 4a26e6d

Upload eval_results.json with huggingface_hub

Browse files

Files changed (1) hide show

eval_results.json +98 -0

eval_results.json ADDED Viewed

	@@ -0,0 +1,98 @@

+{
+  "base_label": "./sft_checkpoint (PEFT on unsloth/Qwen2.5-1.5B-Instruct)",
+  "trained_label": "./grpo_checkpoint (PEFT on unsloth/Qwen2.5-1.5B-Instruct)",
+  "seed": 1234,
+  "episodes_per_level": 4,
+  "base": {
+    "1": {
+      "violations_per_episode": 0.0,
+      "ordering_rate": 1.0,
+      "close_rate": 1.0,
+      "correct_disqual_rate": 0.0,
+      "mean_final_reward": 0.3566666666666667,
+      "mean_cum_reward": 1.09,
+      "mean_turns": 7.0,
+      "n_episodes": 4,
+      "n_disqual_cases": 0
+    },
+    "2": {
+      "violations_per_episode": 1.0,
+      "ordering_rate": 0.8,
+      "close_rate": 0.0,
+      "correct_disqual_rate": 0.0,
+      "mean_final_reward": -0.08000000000000002,
+      "mean_cum_reward": 0.5800000000000001,
+      "mean_turns": 6.0,
+      "n_episodes": 4,
+      "n_disqual_cases": 0
+    },
+    "3": {
+      "violations_per_episode": 1.0,
+      "ordering_rate": 0.5714285714285714,
+      "close_rate": 0.0,
+      "correct_disqual_rate": 0.0,
+      "mean_final_reward": -0.08000000000000002,
+      "mean_cum_reward": 0.5342857142857143,
+      "mean_turns": 6.0,
+      "n_episodes": 4,
+      "n_disqual_cases": 0
+    },
+    "4": {
+      "violations_per_episode": 0.0,
+      "ordering_rate": 1.0,
+      "close_rate": 0.0,
+      "correct_disqual_rate": 1.0,
+      "mean_final_reward": 0.2,
+      "mean_cum_reward": 0.7,
+      "mean_turns": 6.0,
+      "n_episodes": 4,
+      "n_disqual_cases": 4
+    }
+  },
+  "trained": {
+    "1": {
+      "violations_per_episode": 0.25,
+      "ordering_rate": 0.9166666666666666,
+      "close_rate": 0.75,
+      "correct_disqual_rate": 0.0,
+      "mean_final_reward": 0.245,
+      "mean_cum_reward": 0.9783333333333335,
+      "mean_turns": 7.0,
+      "n_episodes": 4,
+      "n_disqual_cases": 0
+    },
+    "2": {
+      "violations_per_episode": 1.0,
+      "ordering_rate": 0.8,
+      "close_rate": 0.0,
+      "correct_disqual_rate": 0.0,
+      "mean_final_reward": -0.08000000000000002,
+      "mean_cum_reward": 0.63,
+      "mean_turns": 6.5,
+      "n_episodes": 4,
+      "n_disqual_cases": 0
+    },
+    "3": {
+      "violations_per_episode": 1.25,
+      "ordering_rate": 0.5714285714285714,
+      "close_rate": 0.0,
+      "correct_disqual_rate": 0.0,
+      "mean_final_reward": -0.08000000000000002,
+      "mean_cum_reward": 0.5392857142857143,
+      "mean_turns": 6.25,
+      "n_episodes": 4,
+      "n_disqual_cases": 0
+    },
+    "4": {
+      "violations_per_episode": 0.0,
+      "ordering_rate": 1.0,
+      "close_rate": 0.0,
+      "correct_disqual_rate": 1.0,
+      "mean_final_reward": 0.2,
+      "mean_cum_reward": 0.7,
+      "mean_turns": 6.0,
+      "n_episodes": 4,
+      "n_disqual_cases": 4
+    }
+  }
+}