Instructions to use Downtown-Case/Deepseek-EVA-32B-DELLA-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Downtown-Case/Deepseek-EVA-32B-DELLA-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Downtown-Case/Deepseek-EVA-32B-DELLA-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Downtown-Case/Deepseek-EVA-32B-DELLA-v1")
model = AutoModelForCausalLM.from_pretrained("Downtown-Case/Deepseek-EVA-32B-DELLA-v1")
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 Downtown-Case/Deepseek-EVA-32B-DELLA-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Downtown-Case/Deepseek-EVA-32B-DELLA-v1

SGLang

How to use Downtown-Case/Deepseek-EVA-32B-DELLA-v1 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 "Downtown-Case/Deepseek-EVA-32B-DELLA-v1" \
    --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": "Downtown-Case/Deepseek-EVA-32B-DELLA-v1",
		"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 "Downtown-Case/Deepseek-EVA-32B-DELLA-v1" \
        --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": "Downtown-Case/Deepseek-EVA-32B-DELLA-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Downtown-Case/Deepseek-EVA-32B-DELLA-v1 with Docker Model Runner:
```
docker model run hf.co/Downtown-Case/Deepseek-EVA-32B-DELLA-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Deepseek-EVA-DELLA-Merge

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

The intent is to make Deepseek R1 32B feel more like a "base model" like EVA-Gutenberg Qwen, adhering to an existing style when writing.

But consider this a quick A/B test between the new DELLA and SCE merging techniques. This is the DELLA merge, with a average density of 0.6 as found to be ideal for DARE in the SCE paper, but a higher epsilon to allow more density varaition: https://arxiv.org/abs/2408.07990

Merge Details

Merge Method

This model was merged using the DELLA merge method using /home/a/Models/Raw/Qwen_Qwen2.5-32B as a base.

Models Merged

The following models were included in the merge:

/home/a/Models/Raw/deepseek-ai_DeepSeek-R1-Distill-Qwen-32B
/home/a/Models/Raw/nbeerbower_EVA-Gutenberg3-Qwen2.5-32B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /home/a/Models/Raw/Qwen_Qwen2.5-32B
  # No parameters necessary for base model
  - model: /home/a/Models/Raw/nbeerbower_EVA-Gutenberg3-Qwen2.5-32B
    parameters:
      weight: 0.5
      density: 0.5
  - model: /home/a/Models/Raw/deepseek-ai_DeepSeek-R1-Distill-Qwen-32B
    parameters:
      weight: 0.5
      density: 0.7
merge_method: della
tokenizer:
  source: "union"
base_model: /home/a/Models/Raw/Qwen_Qwen2.5-32B
chat_template: "deepseek"
parameters:
  int8_mask: true
  epsilon: 0.17
  lambda: 1
dtype: bfloat16

Downloads last month: 10

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for Downtown-Case/Deepseek-EVA-32B-DELLA-v1

Quantizations

2 models

Papers for Downtown-Case/Deepseek-EVA-32B-DELLA-v1

FuseChat: Knowledge Fusion of Chat Models

Paper • 2408.07990 • Published Aug 15, 2024 • 15

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

Paper • 2406.11617 • Published Jun 17, 2024 • 10