Instructions to use DCAgent2/nl2bash-bugs-over5050 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DCAgent2/nl2bash-bugs-over5050 with Transformers:

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

pipe = pipeline("text-generation", model="DCAgent2/nl2bash-bugs-over5050")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DCAgent2/nl2bash-bugs-over5050")
model = AutoModelForCausalLM.from_pretrained("DCAgent2/nl2bash-bugs-over5050")
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 DCAgent2/nl2bash-bugs-over5050 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DCAgent2/nl2bash-bugs-over5050"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DCAgent2/nl2bash-bugs-over5050",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DCAgent2/nl2bash-bugs-over5050

SGLang

How to use DCAgent2/nl2bash-bugs-over5050 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 "DCAgent2/nl2bash-bugs-over5050" \
    --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": "DCAgent2/nl2bash-bugs-over5050",
		"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 "DCAgent2/nl2bash-bugs-over5050" \
        --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": "DCAgent2/nl2bash-bugs-over5050",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DCAgent2/nl2bash-bugs-over5050 with Docker Model Runner:
```
docker model run hf.co/DCAgent2/nl2bash-bugs-over5050
```

penfever commited on Nov 25, 2025

Commit

2b03ae0

verified ·

1 Parent(s): a5ec16d

End of training

Browse files

Files changed (5) hide show

README.md +2 -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

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
 - generated_from_trainer
 model-index:
 - name: nl2bash-bugs-over5050
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 # nl2bash-bugs-over5050
-This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the None dataset.
 ## Model description

 base_model: Qwen/Qwen3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: nl2bash-bugs-over5050
 # nl2bash-bugs-over5050
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the penfever/GLM-4.6-nl2bash-verified-32eps-32k and the penfever/GLM-4.6-inferredbugs-32eps-65k datasets.
 ## Model description

all_results.json ADDED Viewed

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

+{
+    "achieved_tflops_per_gpu": 0.002708354947231431,
+    "achieved_tflops_per_gpu_theoretical": 708.0720536300421,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.059055425226688385,
+    "mfu_percent": 0.00019140317648278665,
+    "mfu_percent_theoretical": 50.04042781837753,
+    "total_flos": 1483460788355072.0,
+    "train_loss": 0.12303723783469668,
+    "train_runtime": 34233.4373,
+    "train_samples_per_second": 3.334,
+    "train_steps_per_second": 0.209,
+    "valid_targets_mean": 2420.6,
+    "valid_targets_min": 743
+}

train_results.json ADDED Viewed

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

+{
+    "achieved_tflops_per_gpu": 0.002708354947231431,
+    "achieved_tflops_per_gpu_theoretical": 708.0720536300421,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.059055425226688385,
+    "mfu_percent": 0.00019140317648278665,
+    "mfu_percent_theoretical": 50.04042781837753,
+    "total_flos": 1483460788355072.0,
+    "train_loss": 0.12303723783469668,
+    "train_runtime": 34233.4373,
+    "train_samples_per_second": 3.334,
+    "train_steps_per_second": 0.209,
+    "valid_targets_mean": 2420.6,
+    "valid_targets_min": 743
+}

trainer_state.json ADDED Viewed

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

training_loss.png ADDED Viewed