Instructions to use basiphobe/sci-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basiphobe/sci-assistant with Transformers:

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

pipe = pipeline("text-generation", model="basiphobe/sci-assistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("basiphobe/sci-assistant")
model = AutoModelForCausalLM.from_pretrained("basiphobe/sci-assistant", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use basiphobe/sci-assistant with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf basiphobe/sci-assistant:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf basiphobe/sci-assistant:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf basiphobe/sci-assistant:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf basiphobe/sci-assistant:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf basiphobe/sci-assistant:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf basiphobe/sci-assistant:Q4_K_M

Use Docker

docker model run hf.co/basiphobe/sci-assistant:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use basiphobe/sci-assistant with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/basiphobe/sci-assistant:Q4_K_M

SGLang

How to use basiphobe/sci-assistant 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 "basiphobe/sci-assistant" \
    --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": "basiphobe/sci-assistant",
		"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 "basiphobe/sci-assistant" \
        --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": "basiphobe/sci-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use basiphobe/sci-assistant with Ollama:
```
ollama run hf.co/basiphobe/sci-assistant:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use basiphobe/sci-assistant with Docker Model Runner:
```
docker model run hf.co/basiphobe/sci-assistant:Q4_K_M
```

Lemonade

How to use basiphobe/sci-assistant with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull basiphobe/sci-assistant:Q4_K_M

Run and chat with the model

lemonade run user.sci-assistant-Q4_K_M

List all available models

lemonade list

Atomic Chat

basiphobe commited on Aug 18, 2025

Commit

5044342

verified ·

1 Parent(s): bf84358

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ The model understands the unique challenges, medical realities, and daily life c
 - **Base Model**: teknium/OpenHermes-2.5-Mistral-7B
 - **Training Method**: QLoRA (4-bit quantization with LoRA adapters)
 - **Training Data**: 119,117 total entries (35,779 domain text + 83,337 instruction pairs)
-- **Hardware**: RTX 4070 Super (8GB VRAM)
 - **Training Time**: ~20 hours total (Phase 1 + Phase 2)
 ## Usage
@@ -355,7 +355,7 @@ Training data underwent extensive preprocessing:
 #### Speeds, Sizes, Times
 - **Total training time:** ~20 hours (8h Phase 1 + 12h Phase 2)
-- **Hardware:** RTX 4070 Super (8GB VRAM)
 - **Final model size:** 30MB (LoRA adapter only)
 - **Base model size:** 7B parameters (not included in adapter)
 - **Training throughput:** ~3.5 samples/second average
@@ -415,7 +415,7 @@ Evaluation considered multiple factors:
 Training carbon emissions estimated using energy consumption data:
-- **Hardware Type:** RTX 4070 Super (8GB VRAM)
 - **Hours used:** ~20 hours total training time
 - **Cloud Provider:** Local training (personal hardware)
 - **Compute Region:** North America
@@ -437,7 +437,7 @@ The use of QLoRA significantly reduced training time and energy consumption comp
 #### Hardware
-- **GPU:** NVIDIA RTX 4070 Super (8GB VRAM)
 - **CPU:** Modern multi-core processor
 - **RAM:** 32GB system memory
 - **Storage:** NVMe SSD for fast data loading

 - **Base Model**: teknium/OpenHermes-2.5-Mistral-7B
 - **Training Method**: QLoRA (4-bit quantization with LoRA adapters)
 - **Training Data**: 119,117 total entries (35,779 domain text + 83,337 instruction pairs)
+- **Hardware**: RTX 4070 Super (12GB VRAM)
 - **Training Time**: ~20 hours total (Phase 1 + Phase 2)
 ## Usage
 #### Speeds, Sizes, Times
 - **Total training time:** ~20 hours (8h Phase 1 + 12h Phase 2)
+- **Hardware:** RTX 4070 Super (12GB VRAM)
 - **Final model size:** 30MB (LoRA adapter only)
 - **Base model size:** 7B parameters (not included in adapter)
 - **Training throughput:** ~3.5 samples/second average
 Training carbon emissions estimated using energy consumption data:
+- **Hardware Type:** RTX 4070 Super (12GB VRAM)
 - **Hours used:** ~20 hours total training time
 - **Cloud Provider:** Local training (personal hardware)
 - **Compute Region:** North America
 #### Hardware
+- **GPU:** NVIDIA RTX 4070 Super (12GB VRAM)
 - **CPU:** Modern multi-core processor
 - **RAM:** 32GB system memory
 - **Storage:** NVMe SSD for fast data loading