Instructions to use MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal with Transformers:

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

pipe = pipeline("text-generation", model="MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal")
model = AutoModelForCausalLM.from_pretrained("MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal")
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]:]))

PEFT
How to use MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal

SGLang

How to use MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal 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 "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal" \
    --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": "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
		"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 "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal" \
        --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": "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal with Docker Model Runner:
```
docker model run hf.co/MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal
```

qwen2.5-coder-1.5b-CodeSLM-Nihal

A QLoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct into a terse, code-first Python assistant, built as a hands-on, phase-by-phase fine-tuning learning project on a single 8 GB consumer GPU (NVIDIA RTX 5060).

The base model is a capable coder but chronically verbose — every answer trails a prose essay. This fine-tune trains it to reply with correct, minimal code and nothing else.

Headline result

On 18 held-out prompts (greedy decoding), average output length dropped from 272 to 60 tokens (−78%) while core algorithm correctness was preserved.

Training curve

Checkpoint (epoch)	Validation loss
0.13	0.5157
0.38	0.5020
0.88	0.4927
1.00	0.4928

Train and validation loss tracked each other the entire run — clean convergence, no overfitting. Final train loss 0.4906; validation mean token-accuracy ~85.4%.

These are training/next-token metrics plus a qualitative 18-prompt comparison. No standardized code benchmark (HumanEval/MBPP) was run.

Training details


Base	`Qwen/Qwen2.5-Coder-1.5B-Instruct`
Method	QLoRA (4-bit NF4 base + LoRA), completion-only loss
Dataset	`sahil2801/CodeAlpaca-20k` → Qwen ChatML (19,020 train / 1,002 val)
LoRA	r=16, α=32, dropout=0.05, targets q/k/v/o/gate/up/down
Trainable params	18.46M (~1.18%)
Schedule	1 epoch, 1,189 steps, LR 2e-4 cosine + 3% warmup
Batch	2 × 8 grad-accum = effective 16
Optimizer	paged_adamw_8bit, bf16, gradient checkpointing, max_len 1024
Hardware	1× RTX 5060 (8 GB), ~50 min, peak VRAM 3.32 GB

Files in this repo

Root — merged fp16 model (Transformers format); load directly with from_pretrained.
adapter/ — the standalone LoRA adapter (~36 MB) to apply onto the base yourself.
gguf/ — …-f16.gguf (full precision) and …-Q4_K_M.gguf (~986 MB) for llama.cpp / Ollama.

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
m = "MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, device_map="auto")
msgs = [{"role": "user", "content": "Write a Python function that reverses a string without slicing."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=128)[0][ids.shape[1]:], skip_special_tokens=True))

Ollama

ollama run mohdnihalll03/qwen2.5-coder-1.5b-codeslm-nihal

Prompt format: Qwen2.5 ChatML. Suggested: temperature 0.2, stop on <|im_start|> / <|im_end|>.

Limitations

Style over correctness: fine-tuning changed formatting far more than correctness. A few subtle base-model bugs persist (an email-regex character-class quirk; a @timer decorator missing functools.wraps), and one bracket-matching answer regressed to a logic bug on empty-stack input. Review generated code before use.
Python-focused; 1.5B params + 4-bit quantization — not a substitute for a large frontier model.
Occasional instruction drift (print vs return, tabulation vs memoization).

Attribution

Data: sahil2801/CodeAlpaca-20k
Fine-tuned by Nihal as a QLoRA learning project (TRL / PEFT / bitsandbytes).

Downloads last month: 410

Safetensors

Model size

2B params

Tensor type

F16

Model tree for MohdNihal03/qwen2.5-coder-1.5b-CodeSLM-Nihal

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B-Instruct

Adapter

(129)

this model

MohdNihal03
/

qwen2.5-coder-1.5b-CodeSLM-Nihal