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

Libraries

How to use Lambent/qwen2.5-reinstruct-alternate-lumen-14B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lambent/qwen2.5-reinstruct-alternate-lumen-14B"
# 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-reinstruct-alternate-lumen-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lambent/qwen2.5-reinstruct-alternate-lumen-14B

SGLang

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

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

qwen2.5-reinstruct-alternate-lumen-14B / README.md

Lambent

Improve language tag (#3)

a45d1d2 verified about 1 year ago

preview code

raw

history blame contribute delete

5.1 kB

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Qwen/Qwen2.5-14B-Instruct
  - Lambent/qwen2.5-lumen-rebased-14B
language:
  - zho
  - eng
  - fra
  - spa
  - por
  - deu
  - ita
  - rus
  - jpn
  - kor
  - vie
  - tha
  - ara
model-index:
  - name: qwen2.5-reinstruct-alternate-lumen-14B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 47.94
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 48.99
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 19.79
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 16.89
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 19.62
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 48.76
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Lambent/qwen2.5-reinstruct-alternate-lumen-14B
          name: Open LLM Leaderboard

qwenreinstruct

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

Merge Details

Extracted an approximate LoRA of v000000/Qwen2.5-Lumen-14B, rank 128 difference between that and Instruct, and first applied this to Lambent/qwen2.5-14B-alternate-instruct-slerp which had no issues with EQ-Bench.

Then, here, re-applied a density and weight of original Instruct which in previous merges gave me no issues with EQ-Bench.

This one has EQ-Bench of 77.6713 and no "emotions don't match reference error" (if possibly still one not parsed). This is similar to Lumen and original Instruct and slightly exceeds both (within margin of error). My hope is that it has healed Instruct somewhat and regained its intelligence.

Merge Method

This model was merged using the della merge method using Lambent/qwen2.5-lumen-rebased-14B as a base.

Models Merged

The following models were included in the merge:

Qwen/Qwen2.5-14B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-14B-Instruct
    parameters:
      weight: 0.3
      density: 0.4
merge_method: della
base_model: Lambent/qwen2.5-lumen-rebased-14B
parameters:
  epsilon: 0.05
  lambda: 1
dtype: bfloat16
tokenizer_source: base

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	33.66
IFEval (0-Shot)	47.94
BBH (3-Shot)	48.99
MATH Lvl 5 (4-Shot)	19.79
GPQA (0-shot)	16.89
MuSR (0-shot)	19.62
MMLU-PRO (5-shot)	48.76