Instructions to use kshitijthakkar/deepseek-v4-mini-1B-from-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kshitijthakkar/deepseek-v4-mini-1B-from-flash with Transformers:

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

pipe = pipeline("text-generation", model="kshitijthakkar/deepseek-v4-mini-1B-from-flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kshitijthakkar/deepseek-v4-mini-1B-from-flash")
model = AutoModelForCausalLM.from_pretrained("kshitijthakkar/deepseek-v4-mini-1B-from-flash")
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 kshitijthakkar/deepseek-v4-mini-1B-from-flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kshitijthakkar/deepseek-v4-mini-1B-from-flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kshitijthakkar/deepseek-v4-mini-1B-from-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kshitijthakkar/deepseek-v4-mini-1B-from-flash

SGLang

How to use kshitijthakkar/deepseek-v4-mini-1B-from-flash 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 "kshitijthakkar/deepseek-v4-mini-1B-from-flash" \
    --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": "kshitijthakkar/deepseek-v4-mini-1B-from-flash",
		"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 "kshitijthakkar/deepseek-v4-mini-1B-from-flash" \
        --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": "kshitijthakkar/deepseek-v4-mini-1B-from-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kshitijthakkar/deepseek-v4-mini-1B-from-flash with Docker Model Runner:
```
docker model run hf.co/kshitijthakkar/deepseek-v4-mini-1B-from-flash
```

deepseek-v4-mini-1B-from-flash / frozen_keys.json

kshitijthakkar

Partial slice from deepseek-ai/DeepSeek-V4-Flash (16/27 shards)

0073e98 verified about 2 months ago

raw

history blame contribute delete

1.7 kB

	[
	"layers.0.hc_attn_base",
	"layers.0.hc_attn_scale",
	"layers.0.hc_ffn_base",
	"layers.0.hc_ffn_scale",
	"layers.1.hc_attn_base",
	"layers.1.hc_attn_scale",
	"layers.1.hc_ffn_base",
	"layers.1.hc_ffn_scale",
	"layers.2.hc_attn_base",
	"layers.2.hc_attn_scale",
	"layers.2.hc_ffn_base",
	"layers.2.hc_ffn_scale",
	"layers.3.hc_attn_base",
	"layers.3.hc_attn_scale",
	"layers.3.hc_ffn_base",
	"layers.3.hc_ffn_scale",
	"layers.4.hc_attn_base",
	"layers.4.hc_attn_scale",
	"layers.4.hc_ffn_base",
	"layers.4.hc_ffn_scale",
	"layers.5.hc_attn_base",
	"layers.5.hc_attn_scale",
	"layers.5.hc_ffn_base",
	"layers.5.hc_ffn_scale",
	"layers.6.hc_attn_base",
	"layers.6.hc_attn_scale",
	"layers.6.hc_ffn_base",
	"layers.6.hc_ffn_scale",
	"layers.7.hc_attn_base",
	"layers.7.hc_attn_scale",
	"layers.7.hc_ffn_base",
	"layers.7.hc_ffn_scale",
	"layers.8.hc_attn_base",
	"layers.8.hc_attn_scale",
	"layers.8.hc_ffn_base",
	"layers.8.hc_ffn_scale",
	"layers.9.hc_attn_base",
	"layers.9.hc_attn_scale",
	"layers.9.hc_ffn_base",
	"layers.9.hc_ffn_scale",
	"layers.10.hc_attn_base",
	"layers.10.hc_attn_scale",
	"layers.10.hc_ffn_base",
	"layers.10.hc_ffn_scale",
	"layers.11.hc_attn_base",
	"layers.11.hc_attn_scale",
	"layers.11.hc_ffn_base",
	"layers.11.hc_ffn_scale",
	"layers.12.hc_attn_base",
	"layers.12.hc_attn_scale",
	"layers.12.hc_ffn_base",
	"layers.12.hc_ffn_scale",
	"layers.13.hc_attn_base",
	"layers.13.hc_attn_scale",
	"layers.13.hc_ffn_base",
	"layers.13.hc_ffn_scale",
	"layers.14.hc_attn_base",
	"layers.14.hc_attn_scale",
	"layers.14.hc_ffn_base",
	"layers.14.hc_ffn_scale"
	]