Instructions to use lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu with Transformers:

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

pipe = pipeline("text-generation", model="lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu")
model = AutoModelForCausalLM.from_pretrained("lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu

SGLang

How to use lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu 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 "lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu" \
    --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": "lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu",
		"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 "lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu" \
        --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": "lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu with Docker Model Runner:
```
docker model run hf.co/lllqaq/R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu
```

lllqaq commited on Mar 18

Commit

21ec318

verified ·

1 Parent(s): ece0660

Add files using upload-large-folder tool

Browse files

Files changed (1) hide show

README.md +61 -0

README.md ADDED Viewed

	@@ -0,0 +1,61 @@

+---
+library_name: transformers
+license: other
+base_model: AgPerry/Qwen2.5-Coder-7B-Instruct-num07
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# R2EGym-7B-Agent-Coder-Instruct-num07_posttrain_r2egym_32768_8gpu
+This model is a fine-tuned version of [AgPerry/Qwen2.5-Coder-7B-Instruct-num07](https://huggingface.co/AgPerry/Qwen2.5-Coder-7B-Instruct-num07) on the r2egym_sft_trajectories dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+### Training results
+### Framework versions
+- Transformers 4.57.1
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2