Instructions to use cs-552-2026-OAAA/general_knowledge_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-OAAA/general_knowledge_model with Transformers:

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

pipe = pipeline("text-generation", model="cs-552-2026-OAAA/general_knowledge_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-OAAA/general_knowledge_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-OAAA/general_knowledge_model", device_map="auto")
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 Settings

vLLM

How to use cs-552-2026-OAAA/general_knowledge_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs-552-2026-OAAA/general_knowledge_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs-552-2026-OAAA/general_knowledge_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-OAAA/general_knowledge_model

SGLang

How to use cs-552-2026-OAAA/general_knowledge_model 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 "cs-552-2026-OAAA/general_knowledge_model" \
    --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": "cs-552-2026-OAAA/general_knowledge_model",
		"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 "cs-552-2026-OAAA/general_knowledge_model" \
        --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": "cs-552-2026-OAAA/general_knowledge_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-OAAA/general_knowledge_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-OAAA/general_knowledge_model
```

OmarEl03 commited on Jun 9

Commit

f0f1265

verified ·

1 Parent(s): 1429da5

Overwrite with GRPO checkpoint-60 from v7

Browse files

Files changed (4) hide show

TRAINING_INFO.json +4 -21
config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1

TRAINING_INFO.json CHANGED Viewed

@@ -1,23 +1,6 @@
 {
-  "start_model": "/scratch/models/gk_rft_v7_teacher_no_think_from_v5_merged",
-  "teacher_data": "/scratch/mmlu_pro_filtered/teacher_traces/qwen8b_teacher_mmlu_pro_failures_all_wrapped_kept_cleaner.jsonl",
-  "replay_data": null,
-  "method": "v11 targeted SFT: clean Qwen3-8B wrapped teacher traces for MMLU-Pro 8-10 v7 failures",
-  "warning": "Replay data was not used if replay_data is null.",
-  "num_teacher_examples": 597,
-  "num_replay_examples": 0,
-  "num_train_examples_before_tokenization": 597,
-  "num_train_examples_after_tokenization": 597,
-  "num_epochs": 1,
-  "learning_rate": 1e-07,
-  "max_seq_length": 6144,
-  "per_device_batch_size": 1,
-  "gradient_accumulation_steps": 32,
-  "effective_batch_size": 32,
-  "lora_r": 8,
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
-  "system_prompt": "You are a careful multiple-choice reasoning model.",
-  "manual_qwen_chat_format": true,
-  "prompt_loss_masked": true
 }

 {
+  "base_model": "/scratch/models/gk_rft_v7_teacher_no_think_from_v5_merged",
+  "lora_path": "/scratch/models/gk_v18_grpo_from_v7_lora/checkpoint-60",
+  "checkpoint_to_eval": "checkpoint-60",
+  "merged_model_path": "/scratch/models/gk_v18_grpo_from_v7_checkpoint-60_merged"
 }

config.json CHANGED Viewed

@@ -60,4 +60,4 @@
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}

   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
+}

generation_config.json CHANGED Viewed

@@ -6,4 +6,4 @@
   "max_new_tokens": 16384,
   "pad_token_id": 151643,
   "transformers_version": "5.7.0"
-}

   "max_new_tokens": 16384,
   "pad_token_id": 151643,
   "transformers_version": "5.7.0"
+}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c610e29b870f25625f4f6c5c5a9b9735ad312e6601dbafef2682e7add8cc7807
 size 3441185608

 version https://git-lfs.github.com/spec/v1
+oid sha256:710acdd2e3a56bb7fb33429ab6002e18cf6a018b78beca6dc355ef1294fc3c24
 size 3441185608