Instructions to use aethertp/PicoLM-V4-85M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aethertp/PicoLM-V4-85M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="aethertp/PicoLM-V4-85M-Instruct")
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("aethertp/PicoLM-V4-85M-Instruct")
model = AutoModelForCausalLM.from_pretrained("aethertp/PicoLM-V4-85M-Instruct", 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

llama.cpp

How to use aethertp/PicoLM-V4-85M-Instruct with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Use Docker

docker model run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use aethertp/PicoLM-V4-85M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aethertp/PicoLM-V4-85M-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": "aethertp/PicoLM-V4-85M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

SGLang

How to use aethertp/PicoLM-V4-85M-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 "aethertp/PicoLM-V4-85M-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": "aethertp/PicoLM-V4-85M-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 "aethertp/PicoLM-V4-85M-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": "aethertp/PicoLM-V4-85M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use aethertp/PicoLM-V4-85M-Instruct with Ollama:
```
ollama run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use aethertp/PicoLM-V4-85M-Instruct with Docker Model Runner:
```
docker model run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
```

Lemonade

How to use aethertp/PicoLM-V4-85M-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.PicoLM-V4-85M-Instruct-Q4_K_M

List all available models

lemonade list

Atomic Chat

aethertp commited on 3 days ago

Commit

06218d6

verified ·

1 Parent(s): e0e852d

Add header banner

Browse files

Files changed (2) hide show

README.md +3 -0
assets/banner.png +0 -0

README.md CHANGED Viewed

@@ -15,6 +15,8 @@ datasets:
 - HuggingFaceTB/smol-smoltalk
 ---
 # PicoLM-V4-85M-Instruct
 PicoLM-V4-85M-Instruct is a chat model with 84,960,832 parameters. It is [PicoLM-V4-85M](https://huggingface.co/aethertp/PicoLM-V4-85M), a base model trained from scratch for 6.0 billion training tokens (part of them repeated, see the base model card), fine-tuned for two epochs on a mix of mostly synthetic instruction and chat data, a small identity set and a share of pretraining text (about 82 million tokens processed, 41 million per pass). In our probes the fine-tuned model follows some simple single-turn requests (its name and maker, short lists, JSON), ignores strict format and length constraints, failed all three arithmetic questions and two of five fact questions. Multi-turn conversation is largely untested. Read the Limitations section before using it.
@@ -171,6 +173,7 @@ The model is small, and fine-tuning did not change what it knows. It makes factu
 | `model.safetensors` | 339.9 MB | weights in fp32 (`Qwen3ForCausalLM`) |
 | `config.json`, `generation_config.json`, `tokenizer.json`, `tokenizer_config.json` | small | configuration, tokenizer, ChatML chat template (in `tokenizer_config.json`) |
 | `eval_results.json` | small | raw output of the benchmark run above (Instruct and base, with standard errors); one label in it is Turkish (`yeniden koşu` means re-run) |
 | `PicoLM-V4-85M-Instruct-F16.gguf` | 170.9 MB | GGUF, 16-bit floats |
 | `PicoLM-V4-85M-Instruct-Q8_0.gguf` | 91.2 MB | GGUF, 8-bit quantization (recommended) |
 | `PicoLM-V4-85M-Instruct-Q4_K_M.gguf` | 65.2 MB | GGUF, 4-bit quantization (visibly lossy, see below) |

 - HuggingFaceTB/smol-smoltalk
 ---
+![PicoLM](assets/banner.png)
 # PicoLM-V4-85M-Instruct
 PicoLM-V4-85M-Instruct is a chat model with 84,960,832 parameters. It is [PicoLM-V4-85M](https://huggingface.co/aethertp/PicoLM-V4-85M), a base model trained from scratch for 6.0 billion training tokens (part of them repeated, see the base model card), fine-tuned for two epochs on a mix of mostly synthetic instruction and chat data, a small identity set and a share of pretraining text (about 82 million tokens processed, 41 million per pass). In our probes the fine-tuned model follows some simple single-turn requests (its name and maker, short lists, JSON), ignores strict format and length constraints, failed all three arithmetic questions and two of five fact questions. Multi-turn conversation is largely untested. Read the Limitations section before using it.
 | `model.safetensors` | 339.9 MB | weights in fp32 (`Qwen3ForCausalLM`) |
 | `config.json`, `generation_config.json`, `tokenizer.json`, `tokenizer_config.json` | small | configuration, tokenizer, ChatML chat template (in `tokenizer_config.json`) |
 | `eval_results.json` | small | raw output of the benchmark run above (Instruct and base, with standard errors); one label in it is Turkish (`yeniden koşu` means re-run) |
+| `assets/banner.png` | small | header image of this card |
 | `PicoLM-V4-85M-Instruct-F16.gguf` | 170.9 MB | GGUF, 16-bit floats |
 | `PicoLM-V4-85M-Instruct-Q8_0.gguf` | 91.2 MB | GGUF, 8-bit quantization (recommended) |
 | `PicoLM-V4-85M-Instruct-Q4_K_M.gguf` | 65.2 MB | GGUF, 4-bit quantization (visibly lossy, see below) |

assets/banner.png ADDED Viewed