Instructions to use jahyungu/deepseek-llm-7b-chat-v1-Hard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jahyungu/deepseek-llm-7b-chat-v1-Hard with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-llm-7b-chat")
model = PeftModel.from_pretrained(base_model, "jahyungu/deepseek-llm-7b-chat-v1-Hard")

Transformers

How to use jahyungu/deepseek-llm-7b-chat-v1-Hard with Transformers:

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

pipe = pipeline("text-generation", model="jahyungu/deepseek-llm-7b-chat-v1-Hard")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jahyungu/deepseek-llm-7b-chat-v1-Hard", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jahyungu/deepseek-llm-7b-chat-v1-Hard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jahyungu/deepseek-llm-7b-chat-v1-Hard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jahyungu/deepseek-llm-7b-chat-v1-Hard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jahyungu/deepseek-llm-7b-chat-v1-Hard

SGLang

How to use jahyungu/deepseek-llm-7b-chat-v1-Hard 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 "jahyungu/deepseek-llm-7b-chat-v1-Hard" \
    --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": "jahyungu/deepseek-llm-7b-chat-v1-Hard",
		"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 "jahyungu/deepseek-llm-7b-chat-v1-Hard" \
        --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": "jahyungu/deepseek-llm-7b-chat-v1-Hard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jahyungu/deepseek-llm-7b-chat-v1-Hard with Docker Model Runner:
```
docker model run hf.co/jahyungu/deepseek-llm-7b-chat-v1-Hard
```

deepseek-llm-7b-chat-v1-Hard / README.md

jahyungu

Model save

7e52863 verified 7 months ago

preview code

Raw

History Blame Contribute Delete

1.47 kB

metadata

library_name: peft
license: other
base_model: deepseek-ai/deepseek-llm-7b-chat
tags:
  - base_model:adapter:deepseek-ai/deepseek-llm-7b-chat
  - lora
  - transformers
pipeline_tag: text-generation
model-index:
  - name: deepseek-llm-7b-chat-v1-Hard
    results: []

deepseek-llm-7b-chat-v1-Hard

This model is a fine-tuned version of deepseek-ai/deepseek-llm-7b-chat on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1

Training results

Framework versions

PEFT 0.18.1
Transformers 4.56.0
Pytorch 2.10.0+cu130
Datasets 4.5.0
Tokenizers 0.22.2