Instructions to use 1kz/bigcodemax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 1kz/bigcodemax with Transformers:

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

pipe = pipeline("text-generation", model="1kz/bigcodemax")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("1kz/bigcodemax")
model = AutoModelForCausalLM.from_pretrained("1kz/bigcodemax")
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 1kz/bigcodemax with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/1kz/bigcodemax

SGLang

How to use 1kz/bigcodemax 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 "1kz/bigcodemax" \
    --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": "1kz/bigcodemax",
		"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 "1kz/bigcodemax" \
        --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": "1kz/bigcodemax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 1kz/bigcodemax with Docker Model Runner:
```
docker model run hf.co/1kz/bigcodemax
```

1kz commited on Feb 25

Commit

ac35b7c

verified ·

1 Parent(s): a4e0ec8

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -15

README.md CHANGED Viewed

@@ -3,7 +3,9 @@ language:
   - en
 license: apache-2.0
 tags:
   - reasoning
   - instruct
   - 8b
   - 1kz
@@ -13,10 +15,12 @@ pipeline_tag: text-generation
 inference: true
 ---
-# 1kz-Reasoning-8B
-**A compact 8B reasoning model trained by 1kz**
-Strong at logical deduction, math, coding, multi-step problem solving, and long-context reasoning while staying efficient enough to run on a single consumer GPU.
 ## Model Details
@@ -25,15 +29,15 @@ Strong at logical deduction, math, coding, multi-step problem solving, and long-
 - **Context length**: 128K (RoPE scaled)
 - **Architecture**: Llama-3.1 style (same tokenizer & chat template as Meta-Llama-3.1-8B-Instruct)
 - **Base model**: Fine-tuned from a strong 8B checkpoint
-- **Training inspiration**: Huge thanks to **lfm** for the incredible training recipes, data curation ideas, and open-source methodology that made this model possible. Your work continues to push the frontier for accessible high-performance reasoning models! ❤️
-## Intended Use
-- Chain-of-thought reasoning
-- Complex math & science problems
-- Code generation + debugging
-- Agentic workflows
-- Research & education
 ## Quick Start
@@ -42,15 +46,17 @@ from transformers import pipeline
 pipe = pipeline(
     "text-generation",
-    model="1kz/1kz-Reasoning-8B",
     device_map="auto",
     torch_dtype="auto"
 )
 messages = [
-    {"role": "system", "content": "You are a world-class reasoning assistant."},
-    {"role": "user", "content": "Solve this step-by-step: A bat and a ball cost $1.10 in total. The bat costs $1.00 more than the ball. How much does the ball cost?"}
 ]
-output = pipe(messages, max_new_tokens=2048, temperature=0.7, do_sample=True)
-print(output[0]["generated_text"][-1]["content"])

   - en
 license: apache-2.0
 tags:
+  - code
   - reasoning
+  - coding
   - instruct
   - 8b
   - 1kz
 inference: true
 ---
+# bigcodemax
+**Maximum coding + reasoning power in 8B parameters**
+Created by **[1kz](https://huggingface.co/1kz)**
+An 8B model that punches way above its weight in code generation, software engineering, advanced reasoning, math, and long-context understanding.
 ## Model Details
 - **Context length**: 128K (RoPE scaled)
 - **Architecture**: Llama-3.1 style (same tokenizer & chat template as Meta-Llama-3.1-8B-Instruct)
 - **Base model**: Fine-tuned from a strong 8B checkpoint
+- **Training inspiration**: Huge thanks to **lfm** for the incredible training recipes, data curation, synthetic data pipelines, and open methodology that made this model possible. Your work continues to inspire and push the frontier for compact high-performance models! ❤️
+## Strengths
+- Best-in-class code generation, editing, and debugging
+- Strong mathematical & logical reasoning (CoT & ToT)
+- Excellent at understanding and refactoring large codebases
+- Agentic coding, tool use, and multi-step problem solving
+- Fast inference on consumer hardware (single 4090 / 24GB VRAM)
 ## Quick Start
 pipe = pipeline(
     "text-generation",
+    model="1kz/bigcodemax",
     device_map="auto",
     torch_dtype="auto"
 )
 messages = [
+    {"role": "system", "content": "You are bigcodemax, an expert coding and reasoning assistant."},
+    {"role": "user", "content": "Implement a thread-safe LRU Cache in Python with O(1) operations and explain every design choice step-by-step."}
 ]
+output = pipe(messages, max_new_tokens=2048, temperature=0.6, top_p=0.95, do_sample=True)
+print(output[0]["generated_text"][-1]["content"])
+Benchmarks (internal eval)
+Massive thank you to lfm — without your public training logs, data mixing strategies, and relentless open-source experimentation, a model this capable at only 8B would not exist. You're building the future of accessible frontier intelligence. 🚀