Instructions to use gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1 with Transformers:

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

pipe = pipeline("text-generation", model="gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1")
model = AutoModelForCausalLM.from_pretrained("gerasmark/Mistral-7B-Instruct-v0.3-Forensics-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 gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gerasmark/Mistral-7B-Instruct-v0.3-Forensics-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": "gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1

SGLang

How to use gerasmark/Mistral-7B-Instruct-v0.3-Forensics-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 "gerasmark/Mistral-7B-Instruct-v0.3-Forensics-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": "gerasmark/Mistral-7B-Instruct-v0.3-Forensics-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 "gerasmark/Mistral-7B-Instruct-v0.3-Forensics-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": "gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1 with Docker Model Runner:
```
docker model run hf.co/gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Summary

This model is a fine-tuned version of the Mistral-7B-Instruct-v0.3 optimised for answering questions in the domain of forensic investigations. The model has been trained using a specialised dataset titled Advanced_Forensic_Investigations_Knowledge_Library_v1, which consists of approximately 100 domain-specific question-answer pairs. The objective is to support advanced forensic investigative reasoning, rapid knowledge retrieval, and high-precision forensic domain assistance.

Model Details

Model Description

Model type: Instruction-following Language Model (LoRA-based fine-tuning)
Language(s): English
Fine-tuned from model: Mistral-7B-Instruct-v0.3

Training Details

Training Data

Dataset: Advanced_Forensic_Investigations_Knowledge_Library_v1
Data size: ~100 high-quality, domain-specific QA pairs

Training Procedure

Preprocessing

Template: mistral
Token truncation/cutoff: 2048
No vocab resizing or prompt packing

Hyperparameters

Finetuning type: LoRA
Precision: bf16
LoRA rank: 16
LoRA alpha: 32
Batch size: 4
Gradient accumulation: 8
Learning rate: 3e-4
Epochs: 35
LR scheduler: cosine
Quantisation: 4-bit (bitsandbytes)
Cutoff length: 2048

Compute

Training time: close to 30 minutes
Framework: LLaMA-Factory

Evaluation

Testing Data, Factors & Metrics

Metrics Used: BLEU-4, ROUGE-1, ROUGE-2
Results:
- BLEU-4: 100%
- ROUGE-1: 100%
- ROUGE-2: 100%

These scores reflect perfect overlap with reference answers within the scope of the evaluation dataset.

Technical Specifications

Model Architecture and Objective

Base: Transformer (Mistral-7B architecture)
Fine-tuning method: LoRA
Objective: Instruction-following with forensic legal knowledge adaptation

Compute Infrastructure

Hardware: 2xL40s
Software: LLaMA-Factory, PyTorch, Transformers, bitsandbytes

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for gerasmark/Mistral-7B-Instruct-v0.3-Forensics-v1

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Finetuned

(484)

this model

Quantizations

1 model