Instructions to use pratinavseth/cricket-captain-warmup-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pratinavseth/cricket-captain-warmup-stage2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "pratinavseth/cricket-captain-warmup-stage2")

Transformers

How to use pratinavseth/cricket-captain-warmup-stage2 with Transformers:

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

pipe = pipeline("text-generation", model="pratinavseth/cricket-captain-warmup-stage2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pratinavseth/cricket-captain-warmup-stage2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pratinavseth/cricket-captain-warmup-stage2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pratinavseth/cricket-captain-warmup-stage2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pratinavseth/cricket-captain-warmup-stage2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pratinavseth/cricket-captain-warmup-stage2

SGLang

How to use pratinavseth/cricket-captain-warmup-stage2 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 "pratinavseth/cricket-captain-warmup-stage2" \
    --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": "pratinavseth/cricket-captain-warmup-stage2",
		"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 "pratinavseth/cricket-captain-warmup-stage2" \
        --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": "pratinavseth/cricket-captain-warmup-stage2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pratinavseth/cricket-captain-warmup-stage2 with Docker Model Runner:
```
docker model run hf.co/pratinavseth/cricket-captain-warmup-stage2
```

CricketCaptain — Warmup Checkpoint (Stage 2)

LoRA adapter for Qwen/Qwen3.5-4B, trained with TRL GRPO in a multi-turn agentic RL loop on a custom OpenEnv cricket environment. This is the warmup checkpoint (5-over curriculum, 25 GRPO steps). The main 20-over T20 run resumes from this adapter.

Training

Base: Qwen/Qwen3.5-4B (bf16)
LoRA: r=64, alpha=128, dropout=0.05; targets q/k/v/o + gate/up/down → 85M trainable (~1.98% of 4.2B)
Algorithm: GRPO via TRL (environment_factory=CricketCaptainToolEnv)
Curriculum: max_overs ∈ [2,2,2,2,2,3,3,3,4,4,5] sampled per rollout
Steps: 25, batch=4, num_generations=4, max_completion_length=4096, max_tool_calling_iterations=240
Optimizer: lr=5e-6, beta=0.0 (no KL ref), temperature=0.9, top_p=0.95
Reward composite: 0.20·r_result + 0.45·r_cricket + 0.25·r_behavior + 0.10·r_validity
- r_cricket — dense per-ball Dream11 fantasy proxy
- r_behavior — coherence + adaptation + opponent_awareness + regret
- r_validity — fraction of legal tool calls
- r_result — match outcome margin / win bonus (rare in 5-over)

Use

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", torch_dtype="bfloat16", device_map="auto")
tok  = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-4B")
model = PeftModel.from_pretrained(base, "pratinavseth/cricket-captain-warmup-stage2")

Status

Warmup only. The trained policy that goes to head-to-head eval is the main run checkpoint (resumed from this one, lr=1e-5, 30 steps at 20-over T20, weights rebalanced to 0.35 / 0.30 / 0.25 / 0.10).

Repo: https://github.com/pratinavseth/cricket-captain-llm (OpenEnv hackathon submission).

Framework versions

PEFT 0.19.1

Downloads last month: 3

Model tree for pratinavseth/cricket-captain-warmup-stage2

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5498)

this model