Instructions to use sandeeprdy1729/TIMPS-Coder-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandeeprdy1729/TIMPS-Coder-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="sandeeprdy1729/TIMPS-Coder-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sandeeprdy1729/TIMPS-Coder-0.5B")
model = AutoModelForCausalLM.from_pretrained("sandeeprdy1729/TIMPS-Coder-0.5B")
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]:]))

MLX

How to use sandeeprdy1729/TIMPS-Coder-0.5B 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("sandeeprdy1729/TIMPS-Coder-0.5B")

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)

Inference
Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use sandeeprdy1729/TIMPS-Coder-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sandeeprdy1729/TIMPS-Coder-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sandeeprdy1729/TIMPS-Coder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sandeeprdy1729/TIMPS-Coder-0.5B

SGLang

How to use sandeeprdy1729/TIMPS-Coder-0.5B 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 "sandeeprdy1729/TIMPS-Coder-0.5B" \
    --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": "sandeeprdy1729/TIMPS-Coder-0.5B",
		"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 "sandeeprdy1729/TIMPS-Coder-0.5B" \
        --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": "sandeeprdy1729/TIMPS-Coder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Pi new

How to use sandeeprdy1729/TIMPS-Coder-0.5B with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sandeeprdy1729/TIMPS-Coder-0.5B"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "sandeeprdy1729/TIMPS-Coder-0.5B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sandeeprdy1729/TIMPS-Coder-0.5B 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 "sandeeprdy1729/TIMPS-Coder-0.5B"

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 sandeeprdy1729/TIMPS-Coder-0.5B

Run Hermes

hermes

MLX LM

How to use sandeeprdy1729/TIMPS-Coder-0.5B with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "sandeeprdy1729/TIMPS-Coder-0.5B"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "sandeeprdy1729/TIMPS-Coder-0.5B"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "sandeeprdy1729/TIMPS-Coder-0.5B",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use sandeeprdy1729/TIMPS-Coder-0.5B with Docker Model Runner:
```
docker model run hf.co/sandeeprdy1729/TIMPS-Coder-0.5B
```

TIMPS-Coder-0.5B / README.md

sandeeprdy1729

Upload README.md with huggingface_hub

236e77a verified 12 days ago

preview code

raw

history blame contribute delete

5.59 kB

metadata

language:
  - en
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
tags:
  - code
  - bug-fixing
  - code-review
  - qwen2
  - lora
  - mlx
  - ollama
  - chatml
pipeline_tag: text-generation
library_name: transformers

TIMPS-Coder v3 — Elite Bug-Fixing Assistant (0.5B)

A 0.5B parameter coding model fine-tuned to think before it codes — specialising in bug analysis, code review, algorithm problem-solving, and agentic planning.
Built by Sandeep Reddy · TIMPS · Made in India 🇮🇳

Model Summary

Field	Value
Base model	`Qwen/Qwen2.5-Coder-0.5B-Instruct` (Alibaba Cloud)
Architecture	Qwen2 Transformer — 494M parameters
Fine-tuning method	LoRA (rank=16, 16 layers) via MLX-LM
Context window	4096 tokens
Quantization	Q4_K_M GGUF (Ollama) / BF16 safetensors (HuggingFace)
Chat template	ChatML (`<
License	Apache 2.0
Training hardware	Apple M-series (Mac M1/M2/M3, 8 GB RAM)

Benchmark Results — 25 Tests, 5 Dimensions

Evaluated on 3_benchmark_ollama.py.
Scoring: 2 pts = complete correct answer with code · 1 pt = partial · 0 = wrong/refused.

Dimension	Score	%
🐛 Bug Fix	9 / 10	90%
🔧 SWE / Repo-level	9 / 10	90%
⚡ Algorithms	9 / 10	90%
🔍 Code Review	8 / 10	80%
🤖 Agentic Reasoning	9 / 10	90%
TOTAL	44 / 50	88%

Quick Start

Ollama (recommended)

ollama pull sandeeprdy1729/timps-coder
ollama run sandeeprdy1729/timps-coder

Python (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model     = AutoModelForCausalLM.from_pretrained("sandeeprdy1729/TIMPS-Coder-0.5B")
tokenizer = AutoTokenizer.from_pretrained("sandeeprdy1729/TIMPS-Coder-0.5B")

messages = [
    {"role": "system",  "content": "You are TIMPS-Coder v3. THINK through the root cause, FIX with complete code, VERIFY edge cases."},
    {"role": "user",    "content": "Fix: `data['user']['email']` throws KeyError when email is absent."},
]
text   = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
out    = model.generate(**inputs, max_new_tokens=700, temperature=0.1, do_sample=True)
print(tokenizer.decode(out[0], skip_special_tokens=True))

MLX (Mac Apple Silicon)

pip install mlx-lm
mlx_lm.generate \
  --model sandeeprdy1729/TIMPS-Coder-0.5B \
  --max-tokens 700 --temp 0.1 \
  --prompt '<|im_start|>system
You are TIMPS-Coder v3. THINK through the root cause, FIX with complete code, VERIFY edge cases.<|im_end|>
<|im_start|>user
Fix the race condition: two threads increment self.count += 1 simultaneously.<|im_end|>
<|im_start|>assistant
'

Training Details

Fine-tuning Configuration

Parameter	Value
Base model	`Qwen/Qwen2.5-Coder-0.5B-Instruct`
Fine-tuning method	LoRA (Supervised Fine-Tuning)
LoRA rank	16
Learning rate	5e-6
Iterations	3,000
Batch size	1 (grad accum ×4)
Max sequence length	2048 tokens
Framework	MLX-LM on Apple Silicon
Peak RAM	~5.5 GB

Training Data

Dataset	Type	Approx. Samples
`newfacade/LeetCodeDataset`	Algorithm problems with solutions	~2,500
`SWE-bench/SWE-bench_Verified`	Real GitHub issue → patch	~400
`TIGER-Lab/SWE-Next-SFT-Trajectories`	Agentic edit traces	~2,000
`WaltonFuture/agentic-sft-new`	Tool use + bash planning	~3,000
Custom TIMPS bug-fix corpus	Hand-curated bug/fix pairs	~500
Total		~8,400 samples

All samples formatted in ChatML with THINK → FIX → VERIFY answer structure.

Capabilities

Does well	Limitations
Bug root-cause analysis with explanation	Complex multi-file refactors
SQL injection, race condition, memory leak detection	May miss subtle business-logic bugs
O-notation analysis and algorithm optimisation	Not a replacement for static analysis tools
LeetCode medium-level algorithm problems	Hard competitive programming problems
GitHub Actions / CI YAML generation	Not trained on Terraform, CDK

Usage Tips

Temperature: Keep at 0.1 — higher values increase hallucination on a 0.5B model
Context: Include the full function/class when asking for a bug fix
Verification: Always test generated code. Even at 88% accuracy, edge cases exist
System prompt: Required for best results — see the Quick Start examples above

Training Code

Full training pipeline available at:
https://github.com/Sandeeprdy1729/TIMPS-Coder

License

Apache 2.0 — free to use, modify, and distribute commercially.
Base model (Qwen2.5-Coder-0.5B-Instruct) is also Apache 2.0.