Instructions to use Lambent/qwen2.5-14B-alternate-instruct-slerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lambent/qwen2.5-14B-alternate-instruct-slerp with Transformers:

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

pipe = pipeline("text-generation", model="Lambent/qwen2.5-14B-alternate-instruct-slerp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Lambent/qwen2.5-14B-alternate-instruct-slerp")
model = AutoModelForMultimodalLM.from_pretrained("Lambent/qwen2.5-14B-alternate-instruct-slerp")
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 Lambent/qwen2.5-14B-alternate-instruct-slerp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lambent/qwen2.5-14B-alternate-instruct-slerp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lambent/qwen2.5-14B-alternate-instruct-slerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lambent/qwen2.5-14B-alternate-instruct-slerp

SGLang

How to use Lambent/qwen2.5-14B-alternate-instruct-slerp 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 "Lambent/qwen2.5-14B-alternate-instruct-slerp" \
    --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": "Lambent/qwen2.5-14B-alternate-instruct-slerp",
		"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 "Lambent/qwen2.5-14B-alternate-instruct-slerp" \
        --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": "Lambent/qwen2.5-14B-alternate-instruct-slerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lambent/qwen2.5-14B-alternate-instruct-slerp with Docker Model Runner:
```
docker model run hf.co/Lambent/qwen2.5-14B-alternate-instruct-slerp
```

qwenselfinstructalt

This is a merge of pre-trained language models created using mergekit.

Merge Details

Same idea as Lambent/qwen2.5-14B-selfmerge-A, but training the base model on an ~20M token instruct and continued pretraining dataset first.

Hope is the lightweight instruction tuning might add some synergy with the original instruct.

Testing: eq-bench showed no syntax errors and result was 75.6984, closer to original instruct value of 76.9195 than selfmerge-A (which had 73.8068).

Subsets of mrfakename/Capybara-ShareGPT, abacusai/SystemChat-1.1, anthracite-org/nopm_claude_writing_fixed and fineweb-edu were used for the alternate training.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Lambent/alternate-instruct-qwen2.5-14B
merge_method: slerp
base_model: Qwen/Qwen2.5-14B-Instruct
parameters:
  t:
    - value: [0, 0, 0.3, 0.4, 0.5, 0.6, 0.5, 0.4, 0.3, 0, 0]
dtype: bfloat16

Downloads last month: 2

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for Lambent/qwen2.5-14B-alternate-instruct-slerp

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Finetuned

(420)

this model