Instructions to use reallexi/lexi-coder-v5.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reallexi/lexi-coder-v5.1 with Transformers:

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

pipe = pipeline("text-generation", model="reallexi/lexi-coder-v5.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reallexi/lexi-coder-v5.1")
model = AutoModelForCausalLM.from_pretrained("reallexi/lexi-coder-v5.1", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reallexi/lexi-coder-v5.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reallexi/lexi-coder-v5.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reallexi/lexi-coder-v5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/reallexi/lexi-coder-v5.1

SGLang

How to use reallexi/lexi-coder-v5.1 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 "reallexi/lexi-coder-v5.1" \
    --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": "reallexi/lexi-coder-v5.1",
		"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 "reallexi/lexi-coder-v5.1" \
        --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": "reallexi/lexi-coder-v5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use reallexi/lexi-coder-v5.1 with Docker Model Runner:
```
docker model run hf.co/reallexi/lexi-coder-v5.1
```

lexi-coder-v5.1

lexi-coder-v5.1 by Reallexi LLC AI Model Builder — llm.reallexi.io

A standalone model of 7.25B parameters, derived from mistralai/Mistral-7B-Instruct-v0.3.

The adapter has been merged into the base weights, so no PEFT adapter is needed at runtime.

Size and requirements


Parameters	7,254,839,296 (7.25B)
Weights on disk	13.50 GB
Trained context length	1,024 tokens
Base model	`mistralai/Mistral-7B-Instruct-v0.3`

Approximate memory to hold the weights. Add context and runtime overhead on top.

Precision	Weights
FP16 / BF16	13.51 GB
8-bit (Q8_0)	6.76 GB
4-bit (Q4_K_M)	3.72 GB

Training


Strategy	lora
Adapter	Auto LoRA
LoRA rank / alpha	8 / 16
Dataset	`mteb/CodeRAGStackoverflowPosts_unconverted`
Samples learned	107,500 (through phase 43 of 10000)
Training steps	7,500
Epochs	3

Before / after samples

The same prompts, drawn from the training data, run through the base model before training and the finished model after. This shows what the run changed on representative prompts -- it is not a benchmark. Full outputs are in SAMPLES.md and samples.json alongside this file.

Prompt: Q: What is RESTful programming? What exactly is RESTful programming? A: REST is using the various HTTP methods (mainly GET/PUT/DELETE)

Before: to perform CRUD operations on resources....

A: REST is a design pattern for web services.......................................................

After: to perform CRUD operations on a resource

Prompt: Q: MSIL : Superfluous branch Consider this C# snippet: static string input = null; static string output = null; static

Before: void Main() { input = Console.ReadLine();..Output = input;. }.. The output is: .method private hidebysig static string Main() cil managed {.method assembly extern 0x00000000 0x00000000 0x000
After: void Main() { input = "Hello World"; output = "Goodbye World"; }

The compiler generates the following MSIL: .method private static string Main() { .maxstack 8 .locals init ([0] string input, [1] string output) .locals init ([2] string input

Prompt: Q: Resolving the "most derived" method in a virtual override I have a simple base class and derived class: class

Before: Base { public virtual void DoSomething() {..;}..;. }. class Derived : Base {.*.}

I have a base class method that is overridden in the derived class................................

After: Base { public virtual void DoSomething() { Console .WriteLine("Base"); } } } } } } } } } }

Training curve

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("lexi-coder-v5.1")
tokenizer = AutoTokenizer.from_pretrained("lexi-coder-v5.1")

License and attribution

The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing.

Base model: mistralai/Mistral-7B-Instruct-v0.3
Training data: mteb/CodeRAGStackoverflowPosts_unconverted

Produced by Reallexi LLC AI Model Builder from training job #1810. Core: https://llm.reallexi.io

Who, where, and what platform trained this?

Produced by Reallexi LLC on Reallexi AI Model Builder, a local-first training platform (https://llm.reallexi.io). Hugging Face repository: reallexi/lexi-coder-v5.1. Copyright (c) 2026 Reallexi LLC. All rights reserved.

Downloads last month: 202

Safetensors

Model size

7B params

Tensor type

F16

Model tree for reallexi/lexi-coder-v5.1

Base model

mistralai/Mistral-7B-v0.3

Finetuned

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

Adapter

(846)

this model

Adapters

2 models