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", trust_remote_code=True)
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("reallexi/lexi-coder-v5.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("reallexi/lexi-coder-v5.1", trust_remote_code=True, 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 reallexi/lexi-coder-v5.1 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 reallexi/lexi-coder-v5.1:F16
# Run inference directly in the terminal:
llama cli -hf reallexi/lexi-coder-v5.1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf reallexi/lexi-coder-v5.1:F16
# Run inference directly in the terminal:
llama cli -hf reallexi/lexi-coder-v5.1:F16

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 reallexi/lexi-coder-v5.1:F16
# Run inference directly in the terminal:
./llama-cli -hf reallexi/lexi-coder-v5.1:F16

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 reallexi/lexi-coder-v5.1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf reallexi/lexi-coder-v5.1:F16

Use Docker

docker model run hf.co/reallexi/lexi-coder-v5.1:F16

LM Studio
Jan

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:F16

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?"
			}
		]
	}'

Ollama
How to use reallexi/lexi-coder-v5.1 with Ollama:
```
ollama run hf.co/reallexi/lexi-coder-v5.1:F16
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reallexi/lexi-coder-v5.1:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "reallexi/lexi-coder-v5.1:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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:F16
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull reallexi/lexi-coder-v5.1:F16

Run and chat with the model

lemonade run user.lexi-coder-v5.1-F16

List all available models

lemonade list

Hermes Agent

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reallexi/lexi-coder-v5.1:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default reallexi/lexi-coder-v5.1:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf reallexi/lexi-coder-v5.1:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "reallexi/lexi-coder-v5.1:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

lexi-coder-v5.1 / samples.json

reallexi

Publish Reallexi job #161: Lexi Coder v5.1 101k phases

10c1515 verified about 2 months ago

Raw History Blame Contribute Delete

4.42 kB

	{
	"prompts": [
	"def partition(p, r): i = p for j in range(p, r): if A[r][1] >= A[j][1]: A[i], A[j] = A[j], A[i]",
	"{i : Node(None, None, None) for i in range(n)} # \u60c5\u5831\u3092\u5165\u308c\u308bdict\u3092Node\u30af\u30e9\u30b9\u3067\u4f5c\u6210 for _ in range(n): # \u5909\u6570\u540d\u3092\u300c _ \u300d\u306b\u3059\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u3001\u300c\u305d\u306e\u5909\u6570\u3092\u4f7f\u3063\u3066\u3044\u306a\u3044\u300d\u3053\u3068\u3092\u8868\u73fe\u3057\u3066\u3044\u308b\uff08Python\u306e\u7fd2\u6163\uff09 tmp",
	"rmat(node_id), end = '') _pre_walk(self.nodes[node_id].left_child) _pre_walk(self.nodes[node_id].right_child) _pre_walk(self.root_id) print('') def inorder_walk(self): print('Inorder') root_node = self.nodes[self.root_id] def _in_walk(node_id): if node_id != -1:"
	],
	"before": [
	{
	"prompt": "def partition(p, r): i = p for j in range(p, r): if A[r][1] >= A[j][1]: A[i], A[j] = A[j], A[i]",
	"output": "i += 1 return partition(p, r) if partition(p, r) == partition(p, r): return partition(p, r) else: return partition(p, r)\n\nn = int(input())\nA = [tuple(map(int, input().split())) for _ in range(n)]\nprint(*partition(0, n)[1:]) for i in range(n) if partition(0,"
	},
	{
	"prompt": "{i : Node(None, None, None) for i in range(n)} # \u60c5\u5831\u3092\u5165\u308c\u308bdict\u3092Node\u30af\u30e9\u30b9\u3067\u4f5c\u6210 for _ in range(n): # \u5909\u6570\u540d\u3092\u300c _ \u300d\u306b\u3059\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u3001\u300c\u305d\u306e\u5909\u6570\u3092\u4f7f\u3063\u3066\u3044\u306a\u3044\u300d\u3053\u3068\u3092\u8868\u73fe\u3057\u3066\u3044\u308b\uff08Python\u306e\u7fd2\u6163\uff09 tmp",
	"output": "= input().split() # \u5909\u6570\u540d\u3068\u5024\u3092\u5165\u308c\u308b tmp[0] = tmp[0].strip() # \u5909\u6570\u540d\u3092\u5165\u308c\u308b tmp[1] = tmp[1].strip() # \u5024\u3092\u5165\u308c\u308b tmp[2] = tmp[2].strip() # \u5024\u3092\u5165\u308c\u308b tmp[3] = tmp[3].strip() #"
	},
	{
	"prompt": "rmat(node_id), end = '') _pre_walk(self.nodes[node_id].left_child) _pre_walk(self.nodes[node_id].right_child) _pre_walk(self.root_id) print('') def inorder_walk(self): print('Inorder') root_node = self.nodes[self.root_id] def _in_walk(node_id): if node_id != -1:",
	"output": "_in_walk(self.nodes[node_id].left_child) print(str(self.nodes[node_id].value)) _in_walk(self.nodes[node_id].right_child) def _post_walk(self, node_id, end = ''): if node_id != -1: _post_walk(self.nodes[node_id].left_child) print(str(self.nodes[node_id].value)) _post_walk(self.nodes[node_id].right"
	}
	],
	"after": [
	{
	"prompt": "def partition(p, r): i = p for j in range(p, r): if A[r][1] >= A[j][1]: A[i], A[j] = A[j], A[i]",
	"output": "i += 1 return i\ndef quicksort(p, r): if p < r: i = partition(p, r) quicksort(p, i-1) quicksort(i, r)\ndef mergeSort(p, r): if p < r: q = partition(p, r) mergeSort(p, q) mergeSort(q, r)\ndef printList(): print(\" \", end ="
	},
	{
	"prompt": "{i : Node(None, None, None) for i in range(n)} # \u60c5\u5831\u3092\u5165\u308c\u308bdict\u3092Node\u30af\u30e9\u30b9\u3067\u4f5c\u6210 for _ in range(n): # \u5909\u6570\u540d\u3092\u300c _ \u300d\u306b\u3059\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u3001\u300c\u305d\u306e\u5909\u6570\u3092\u4f7f\u3063\u3066\u3044\u306a\u3044\u300d\u3053\u3068\u3092\u8868\u73fe\u3057\u3066\u3044\u308b\uff08Python\u306e\u7fd2\u6163\uff09 tmp",
	"output": "= input().split() # \u5165\u308c\u3089\u308c\u305f\u5024\u3092\u5909\u6570\u306b\u5165\u308c\u308b tmp[0] = int(tmp[0]) # \u5909\u6570\u306e\u5024\u3092int\u306b\u5909\u63db tmp[1] = int(tmp[1]) # \u5909\u6570\u306e\u5024\u3092int\u306b\u5909\u63db tmp[2] = int(tmp[2]) # \u5909\u6570\u306e\u5024\u3092int\u306b\u5909"
	},
	{
	"prompt": "rmat(node_id), end = '') _pre_walk(self.nodes[node_id].left_child) _pre_walk(self.nodes[node_id].right_child) _pre_walk(self.root_id) print('') def inorder_walk(self): print('Inorder') root_node = self.nodes[self.root_id] def _in_walk(node_id): if node_id != -1:",
	"output": "print(' ', end = '') print(node_id, end = '') _in_walk(self.nodes[node_id].left_child) _in_walk(self.nodes[node_id].right_child) _in_walk(self.nodes[node_id].parent) def post_walk(self): print('Post') root_node = self.nodes[self.root_id] def _post_walk(node_id): if node_id != -1: _post_walk"
	}
	]
	}