Instructions to use nileshc90/apex-code-14b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nileshc90/apex-code-14b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="nileshc90/apex-code-14b-instruct")
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("nileshc90/apex-code-14b-instruct")
model = AutoModelForCausalLM.from_pretrained("nileshc90/apex-code-14b-instruct", 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]:]))

MLX

How to use nileshc90/apex-code-14b-instruct with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("nileshc90/apex-code-14b-instruct")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nileshc90/apex-code-14b-instruct 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 nileshc90/apex-code-14b-instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nileshc90/apex-code-14b-instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nileshc90/apex-code-14b-instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nileshc90/apex-code-14b-instruct: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 nileshc90/apex-code-14b-instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf nileshc90/apex-code-14b-instruct:Q4_K_M

Use Docker

docker model run hf.co/nileshc90/apex-code-14b-instruct:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use nileshc90/apex-code-14b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nileshc90/apex-code-14b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nileshc90/apex-code-14b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nileshc90/apex-code-14b-instruct:Q4_K_M

SGLang

How to use nileshc90/apex-code-14b-instruct 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 "nileshc90/apex-code-14b-instruct" \
    --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": "nileshc90/apex-code-14b-instruct",
		"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 "nileshc90/apex-code-14b-instruct" \
        --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": "nileshc90/apex-code-14b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use nileshc90/apex-code-14b-instruct with Ollama:
```
ollama run hf.co/nileshc90/apex-code-14b-instruct:Q4_K_M
```
Unsloth Desktop

How to use nileshc90/apex-code-14b-instruct with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nileshc90/apex-code-14b-instruct"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nileshc90/apex-code-14b-instruct"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nileshc90/apex-code-14b-instruct with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nileshc90/apex-code-14b-instruct"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nileshc90/apex-code-14b-instruct"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nileshc90/apex-code-14b-instruct",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use nileshc90/apex-code-14b-instruct with Docker Model Runner:
```
docker model run hf.co/nileshc90/apex-code-14b-instruct:Q4_K_M
```

Lemonade

How to use nileshc90/apex-code-14b-instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nileshc90/apex-code-14b-instruct:Q4_K_M

Run and chat with the model

lemonade run user.apex-code-14b-instruct-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nileshc90/apex-code-14b-instruct with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nileshc90/apex-code-14b-instruct"

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 nileshc90/apex-code-14b-instruct

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nileshc90/apex-code-14b-instruct with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nileshc90/apex-code-14b-instruct"

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 "nileshc90/apex-code-14b-instruct" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

nileshc90 commited on 2 days ago

Commit

c3e84b5

verified ·

1 Parent(s): 00fbd7d

docs: add v1.2.0 release notes

Browse files

Files changed (1) hide show

RELEASE_NOTES_v1.2.0.md +51 -0

RELEASE_NOTES_v1.2.0.md ADDED Viewed

	@@ -0,0 +1,51 @@

+# ⚡ ApexCode Release v1.2.0: Bare-Metal Vulkan GPU Acceleration & DiffCodeGen Suite
+ApexCode Release `v1.2.0` introduces native discrete GPU acceleration via Vulkan for legacy Intel + AMD hardware architectures, DiffCodeGen behavioral clustering (*arXiv:2605.20473*), and automated Karpathy-style static analysis tool repair.
+---
+### 🚀 Key Highlights & Breakthroughs
+1. **Hardware-Native Discrete GPU Acceleration (AMD Radeon Pro GDDR6 + Vulkan)**
+   - Resolves the DDR4 memory bandwidth bottleneck (~25 GB/s) on legacy Intel Core i9-9880H bare-metal machines.
+   - Leverages native `llama-server` on `0.0.0.0:8080` targeting the AMD Radeon Pro 5300M/5500M discrete GPU (4 GB GDDR6 @ 192 GB/s).
+   - Generates tokens at **18–26 tokens/second** (up from 1.3 tok/s on CPU-only Docker), collapsing total benchmark wall-clock time from **42.4 minutes down to 5.6 minutes (7.6x overall speedup)**.
+   - Pinned CPU execution strictly preserves thermal safety ($\le 72^\circ\text{C}$, well below the $88^\circ\text{C}$ homelab watchdog ceiling).
+2. **DiffCodeGen Behavioral Clustering Engine (*arXiv:2605.20473*)**
+   - Implements coverage-guided test-time scaling without noisy LLM-as-a-judge overhead.
+   - Samples $K=3$ diverse candidate solutions and runs them against generic boundary test probes in isolated sandboxes (`apex-sandbox-daemon`, `--net=none`, 512MB RAM cap).
+   - Constructs an execution equivalence matrix and selects the medoid of the consensus behavioral cluster.
+3. **Karpathy-Style Software 3.0 External AST Linter Tool Calls**
+   - Deterministic AST visitor (`scripts/ast_linter_tool.py`) audits generated code for common competitive programming bugs:
+     - Repeated `sys.stdin.read()` inside iteration loops (causes premature EOF).
+     - Inadvertent float division (`/`) in integer indexing or slicing.
+     - Hardcoded consecutive array access chains (`a[0] * a[1] * ...`) when array length varies dynamically.
+     - Slow line-by-line I/O warnings.
+   - Dispatches structured violation traces back to the model for single-shot surgical repair.
+4. **Zero-Contamination Boundary**
+   - Strictly prohibits private test inspection or problem-specific heuristics.
+   - All benchmarks evaluated under black-box zero-shot execution.
+---
+### 📊 Benchmark Scorecard: Legacy Hardware (Intel i9-9880H + 32GB RAM + AMD Navi 14)
+LiveCodeBench 25-problem evaluation slice:
+| Configuration | Engine / Hardware | Generation Throughput | Total 25-Prob Wall Clock | Pass@1 Accuracy | Peak CPU Temp |
+| :--- | :--- | :---: | :---: | :---: | :---: |
+| **Docker Baseline (14B)** | Software AVX2 CPU | 1.30 tok/s | 42.4 minutes | 16.0% (4/25) | 90°C (Watchdog kill) |
+| **Zero-Shot Vulkan (7B)** | AMD Navi 14 GDDR6 | 26.38 tok/s | 4.5 minutes | 28.0% (7/25) | 71°C (Safe) |
+| **ApexCode v1.2.0 (Optimized)** | AMD Navi 14 + AST Linter | **18.0 – 26.4 tok/s** | **5.6 minutes** | **32.0% (8/25)** | **72°C (Safe)** |
+---
+### 📦 Hugging Face & Model Hub Artifacts
+- **Repository**: `nileshc90/apex-code-14b-instruct`
+- **Model Presets**:
+  - `apex-code-7b-vulkan` (IQ3_M quantized GGUF, 3.57 GB)
+  - `apex-code-3b-vulkan` (Q4_K_M quantized GGUF, 2.10 GB)
+  - `apex-code-1.5b-vulkan` (Q4_K_M quantized GGUF, 1.11 GB)