Instructions to use laion/r2egym-nl2bash-stack-bugsseq-fixthink-again with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/r2egym-nl2bash-stack-bugsseq-fixthink-again with Transformers:

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

pipe = pipeline("text-generation", model="laion/r2egym-nl2bash-stack-bugsseq-fixthink-again")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/r2egym-nl2bash-stack-bugsseq-fixthink-again")
model = AutoModelForCausalLM.from_pretrained("laion/r2egym-nl2bash-stack-bugsseq-fixthink-again")
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 laion/r2egym-nl2bash-stack-bugsseq-fixthink-again with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/r2egym-nl2bash-stack-bugsseq-fixthink-again"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/r2egym-nl2bash-stack-bugsseq-fixthink-again",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/r2egym-nl2bash-stack-bugsseq-fixthink-again

SGLang

How to use laion/r2egym-nl2bash-stack-bugsseq-fixthink-again 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 "laion/r2egym-nl2bash-stack-bugsseq-fixthink-again" \
    --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": "laion/r2egym-nl2bash-stack-bugsseq-fixthink-again",
		"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 "laion/r2egym-nl2bash-stack-bugsseq-fixthink-again" \
        --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": "laion/r2egym-nl2bash-stack-bugsseq-fixthink-again",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/r2egym-nl2bash-stack-bugsseq-fixthink-again with Docker Model Runner:
```
docker model run hf.co/laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
```

penfever commited on Feb 28

Commit

2f4f59f

verified ·

1 Parent(s): 939f1c1

End of training

Browse files

Files changed (5) hide show

README.md +4 -1
all_results.json +16 -0
train_results.json +16 -0
trainer_state.json +0 -0
training_loss.png +0 -0

README.md CHANGED Viewed

@@ -1,7 +1,10 @@
 ---
 library_name: transformers
 tags:
 - llama-factory
 - generated_from_trainer
 model-index:
 - name: r2egym-nl2bash-stack-bugsseq-fixthink-again
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 # r2egym-nl2bash-stack-bugsseq-fixthink-again
-This model was trained from scratch on the None dataset.
 ## Model description

 ---
 library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: r2egym-nl2bash-stack-bugsseq-fixthink-again
 # r2egym-nl2bash-stack-bugsseq-fixthink-again
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--glm-4.6-r2egym-32ep-32k/snapshots/1b98f51e65d71b6dc9702529884355b93b8b8685_thinking_preprocessed, the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-nl2bash-verified-32eps-32k/snapshots/61e17458d760f1419c4447abbab4fc93118563dd_thinking_preprocessed, the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k/snapshots/1c13e68d92fc88775a6a593c5ca93a4a4bae0a38_thinking_preprocessed and the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-inferredbugs-32eps-65k/snapshots/60d83f48605156a6b9182f9b54c6da2d4dffc061_thinking_preprocessed datasets.
 ## Model description

all_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "achieved_tflops_per_gpu": 5.961135004994871,
+    "achieved_tflops_per_gpu_theoretical": 528.5131118004142,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.04253735765814781,
+    "mfu_percent": 0.6027436809903812,
+    "mfu_percent_theoretical": 53.439141739172314,
+    "total_flos": 3.879727127867687e+18,
+    "train_loss": 0.18411178431570632,
+    "train_runtime": 81354.623,
+    "train_samples_per_second": 2.497,
+    "train_steps_per_second": 0.156,
+    "valid_targets_mean": 4458.2,
+    "valid_targets_min": 1268
+}

train_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "achieved_tflops_per_gpu": 5.961135004994871,
+    "achieved_tflops_per_gpu_theoretical": 528.5131118004142,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.04253735765814781,
+    "mfu_percent": 0.6027436809903812,
+    "mfu_percent_theoretical": 53.439141739172314,
+    "total_flos": 3.879727127867687e+18,
+    "train_loss": 0.18411178431570632,
+    "train_runtime": 81354.623,
+    "train_samples_per_second": 2.497,
+    "train_steps_per_second": 0.156,
+    "valid_targets_mean": 4458.2,
+    "valid_targets_min": 1268
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

training_loss.png ADDED Viewed