Instructions to use luispoveda93/MiniCPM5-2B-catalan-chat-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luispoveda93/MiniCPM5-2B-catalan-chat-v2 with Transformers:

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

pipe = pipeline("text-generation", model="luispoveda93/MiniCPM5-2B-catalan-chat-v2")
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("luispoveda93/MiniCPM5-2B-catalan-chat-v2")
model = AutoModelForCausalLM.from_pretrained("luispoveda93/MiniCPM5-2B-catalan-chat-v2", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use luispoveda93/MiniCPM5-2B-catalan-chat-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luispoveda93/MiniCPM5-2B-catalan-chat-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luispoveda93/MiniCPM5-2B-catalan-chat-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/luispoveda93/MiniCPM5-2B-catalan-chat-v2

SGLang

How to use luispoveda93/MiniCPM5-2B-catalan-chat-v2 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 "luispoveda93/MiniCPM5-2B-catalan-chat-v2" \
    --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": "luispoveda93/MiniCPM5-2B-catalan-chat-v2",
		"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 "luispoveda93/MiniCPM5-2B-catalan-chat-v2" \
        --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": "luispoveda93/MiniCPM5-2B-catalan-chat-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use luispoveda93/MiniCPM5-2B-catalan-chat-v2 with Docker Model Runner:
```
docker model run hf.co/luispoveda93/MiniCPM5-2B-catalan-chat-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiniCPM5-2B-catalan-chat-v2

Conversational Catalan chat model — round 2. A LoRA fine-tune of luispoveda93/MiniCPM5-2B-catalan-chat (itself a LoRA fine-tune of openbmb/MiniCPM5-2B on InstruCAT) focused on multi-turn chat behaviour.

What round 2 added

Round 1 trained on single-turn task instructions (projecte-aina/InstruCAT). Round 2 trains on 23.4K multi-turn Catalan conversations from the chat-dense sources of BSC-LT/ALIA-2606-SFT — the SFT mixture that trained ALIA-40b-instruct-2606:

Source	Conversations	What it teaches
mturn-plus5 (multi-turn augmentation)	5,281	multi-turn conversation flow
eif (exact instruction following)	5,821	instruction adherence
mentor-ca	5,047	mentoring/dialogue
dolly-ca	2,449	open-ended instruction following
coqcat	2,372	conversational QA
alia-identity	1,259	self-identity
system-prompt multi-turn	1,226	system-prompt adherence

All conversations CC-BY-4.0 (removes round-1's non-commercial restriction on the training data; note InstruCAT is still in the round-1 lineage). A Catalan system prompt ("Ets un assistent conversacional que respon sempre en català.") was prepended to conversations lacking one. 400 conversations held out for eval.

Training details

Base: luispoveda93/MiniCPM5-2B-catalan-chat (round-1 merged model)
Method: LoRA r=32 / α=64, all projection layers, lr 1e-4 cosine (gentler than round 1's 2e-4), warmup 50, 1 epoch, effective batch 32 (4 × 8), max_length 2048 packed, bf16, completion-only loss
Scale: ~326 packed steps, 2h19m on A100-large
Observed: train loss 2.44 → ~1.44; eval loss 1.48 → 1.41 → 1.383; token accuracy 0.57 → 0.704 (400-conversation held-out eval)
Training metrics (trackio)

Artifacts

This repo: merged bf16 model (5.0 GB)
Adapter: luispoveda93/MiniCPM5-2B-catalan-chat-v2-lora (on top of the round-1 merged model)
Round 1: luispoveda93/MiniCPM5-2B-catalan-chat · GGUF

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("luispoveda93/MiniCPM5-2B-catalan-chat-v2", dtype="bfloat16")
tok = AutoTokenizer.from_pretrained("luispoveda93/MiniCPM5-2B-catalan-chat-v2")

messages = [
    {"role": "system", "content": "Ets un assistent conversacional que respon sempre en català."},
    {"role": "user", "content": "Hola! Com estàs avui?"},
]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
print(tok.decode(model.generate(inputs, max_new_tokens=256)[0][inputs.shape[1]:], skip_special_tokens=True))

Limitations

2.5B parameters: limited world knowledge and reasoning depth; Catalan conversational style is the training focus.
Round 2 used the chat-dense core of the ALIA mixture (~23.4K conversations); the QA corpora (fineweb-edu, RAG, math) were deliberately excluded to prioritize chat behaviour — task-QA skills come from round 1.
Evaluation is loss/accuracy-based on held-out conversations; no independent Catalan chat benchmark was run.

Downloads last month: 446

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for luispoveda93/MiniCPM5-2B-catalan-chat-v2

Base model

luispoveda93/MiniCPM5-2B-catalan-chat

Finetuned

(2)

this model

Quantizations

1 model