Instructions to use nilenso/Qwen2.5-OCamler-1.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nilenso/Qwen2.5-OCamler-1.5B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nilenso/Qwen2.5-OCamler-1.5B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nilenso/Qwen2.5-OCamler-1.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("nilenso/Qwen2.5-OCamler-1.5B-Instruct")
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 nilenso/Qwen2.5-OCamler-1.5B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nilenso/Qwen2.5-OCamler-1.5B-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": "nilenso/Qwen2.5-OCamler-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nilenso/Qwen2.5-OCamler-1.5B-Instruct

SGLang

How to use nilenso/Qwen2.5-OCamler-1.5B-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 "nilenso/Qwen2.5-OCamler-1.5B-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": "nilenso/Qwen2.5-OCamler-1.5B-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 "nilenso/Qwen2.5-OCamler-1.5B-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": "nilenso/Qwen2.5-OCamler-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nilenso/Qwen2.5-OCamler-1.5B-Instruct with Docker Model Runner:
```
docker model run hf.co/nilenso/Qwen2.5-OCamler-1.5B-Instruct
```

Qwen2.5-OCamler-1.5B-Instruct

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct specialized for generating OCaml code.

Model Details

Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
Fine-tuning Method: Generative Representational Preference Optimization (GRPO) with LoRA
Training Dataset: kiranpg/ocaml-training-problems
Training Code: ocamler-grpo

Training Configuration

GRPO Parameters

Parameter	Value
Batch Size	2
Gradient Accumulation Steps	4
Effective Batch Size	8
Learning Rate	5e-6
Number of Epochs	3
Max Prompt Length	800
Max Completion Length	700
LR Scheduler Type	cosine
Warmup Ratio	0.03
Weight Decay	0.01
Max Grad Norm	1.0
Optimizer	adamw_8bit
Dataloader Num Workers	2

LoRA Configuration

Parameter	Value
LoRA Rank (r)	32
LoRA Alpha	64
LoRA Dropout	0.05

Training Settings

Parameter	Value
Logging Steps	1
Eval Steps	500
Save Steps	100
Save Total Limit	30

GRPO-Specific Parameters

Parameter	Value
Num Generations	8
Temperature	1.0
Beta (KL coefficient)	0.01

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "kiranpg/Qwen2.5-OCamler-1.5B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {"role": "user", "content": "Write an OCaml function to compute the factorial of a number."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Intended Use

This model is designed for generating OCaml code solutions given natural language problem descriptions. It has been fine-tuned on OCaml programming problems using GRPO with real-time feedback from the OCaml compiler and test suite to improve its ability to produce correct, idiomatic OCaml code.

Limitations

The model may not always produce syntactically correct OCaml code
Complex algorithmic problems may require multiple attempts
The model works best with clear, well-specified problem descriptions

Training Infrastructure

Trained using TRL's GRPOTrainer with OCaml compiler verification for rewards. The reward system uses a graduated structure:

Type checking: 25% (partial credit scaled by error count)
Compilation: 10% (partial credit based on type check)
Tests: 65% (all-or-nothing for passing)

Downloads last month: 13

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for nilenso/Qwen2.5-OCamler-1.5B-Instruct

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-Coder-1.5B

Finetuned

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

Adapter

(106)

this model

Adapters

2 models

nilenso
/

Qwen2.5-OCamler-1.5B-Instruct