Instructions to use yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2 with Transformers:

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

pipe = pipeline("text-generation", model="yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2")
model = AutoModelForCausalLM.from_pretrained("yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2

SGLang

How to use yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2 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 "yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2" \
    --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": "yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2",
		"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 "yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2" \
        --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": "yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2 with Docker Model Runner:
```
docker model run hf.co/yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2
```

yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2

Qwen/Qwen2.5-32B-Instruct fine-tuned as a memory model on MuSiQue synthetic QA pairs (msq_subset1000_numsamplingepochs1_crossdoc_entity_combination_v3.json, 664,608 examples) — checkpoint after epoch 2 of 3.

Weights are bf16 safetensors and load with plain transformers (AutoModelForCausalLM.from_pretrained). Use the Qwen chat template.

Training


method	full fine-tuning (FSDP)
trainable params	32,763,876,352 (100.00%)
effective batch size	256 (32/device x 1 accum x 8 GPUs)
learning rate	2e-05 (constant with warmup, warmup ratio 0.05)
epochs	3 (this is epoch 2)
weight decay / max grad norm	0.01 / 1.0
max sequence length	8096
precision	bf16, gradient checkpointing, loss on assistant tokens only
hardware	8x AMD Instinct MI325X
total training wall-clock (3 epochs)	5.79 h (46.3 GPU-h)

Downloads last month: 179

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for yungisimon/Qwen2.5-32B-Instruct-memory-msq-full-ep2

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Finetuned

(1,235)

this model