Instructions to use Raymond-dev-546730/MaterialsAnalyst-AI-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Raymond-dev-546730/MaterialsAnalyst-AI-7B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Raymond-dev-546730/MaterialsAnalyst-AI-7B 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 Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

Use Docker

docker model run hf.co/Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

LM Studio
Jan

vLLM

How to use Raymond-dev-546730/MaterialsAnalyst-AI-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raymond-dev-546730/MaterialsAnalyst-AI-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Raymond-dev-546730/MaterialsAnalyst-AI-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

Ollama
How to use Raymond-dev-546730/MaterialsAnalyst-AI-7B with Ollama:
```
ollama run hf.co/Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Raymond-dev-546730/MaterialsAnalyst-AI-7B with Docker Model Runner:
```
docker model run hf.co/Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M
```

Lemonade

How to use Raymond-dev-546730/MaterialsAnalyst-AI-7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Raymond-dev-546730/MaterialsAnalyst-AI-7B:Q4_K_M

Run and chat with the model

lemonade run user.MaterialsAnalyst-AI-7B-Q4_K_M

List all available models

lemonade list

Atomic Chat

MaterialsAnalyst-AI-7B / Training /Training_Documentation.txt

Raymond-dev-546730

Update Training/Training_Documentation.txt

bd867ce verified over 1 year ago

Raw

History Blame

1.73 kB

	MaterialsAnalyst-AI-7B Training Documentation
	================================================

	Model Training Details
	---------------------

	Base Model: Qwen 2.5 Instruct 7B
	Fine-tuning Method: LoRA (Low-Rank Adaptation)
	Training Infrastructure: Single NVIDIA A100 GPU
	Training Duration: Approximately 5.4 hours
	Training Dataset: Custom curated dataset for materials analysis

	Dataset Specifications
	---------------------

	Total Token Count: 6,441,671
	Total Sample Count: 6,000
	Average Tokens/Sample: 1,073.61
	Dataset Creation: Generated using DeepSeekV3 API

	Training Configuration
	---------------------

	LoRA Parameters:
	- Rank: 32
	- Alpha: 64
	- Dropout: 0.1
	- Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, lm_head

	Training Hyperparameters:
	- Learning Rate: 5e-5
	- Batch Size: 4
	- Gradient Accumulation: 5
	- Effective Batch Size: 20
	- Max Sequence Length: 2048
	- Epochs: 3
	- Warmup Ratio: 0.01
	- Weight Decay: 0.01
	- Max Grad Norm: 1.0
	- LR Scheduler: Cosine

	Hardware & Environment
	---------------------

	GPU: NVIDIA A100 SXM4 (40GB)
	Operating System: Ubuntu
	CUDA Version: 11.8
	PyTorch Version: 2.7.0
	Compute Capability: 8.0
	Optimization: FP16, Gradient Checkpointing

	Training Performance
	---------------------

	Training Runtime: 5.37 hours (19,348 seconds)
	Train Samples/Second: 0.884
	Train Steps/Second: 0.044
	Training Loss (Final): 0.170
	Validation Loss (Final): 0.136
	Total Training Steps: 855