Instructions to use Rahspide/MNN-Pocket-0.3B-RU-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with Transformers:

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

pipe = pipeline("text-generation", model="Rahspide/MNN-Pocket-0.3B-RU-Chat")
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("Rahspide/MNN-Pocket-0.3B-RU-Chat")
model = AutoModelForCausalLM.from_pretrained("Rahspide/MNN-Pocket-0.3B-RU-Chat", 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 Rahspide/MNN-Pocket-0.3B-RU-Chat 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 Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat: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 Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Use Docker

docker model run hf.co/Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rahspide/MNN-Pocket-0.3B-RU-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rahspide/MNN-Pocket-0.3B-RU-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

SGLang

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat 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 "Rahspide/MNN-Pocket-0.3B-RU-Chat" \
    --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": "Rahspide/MNN-Pocket-0.3B-RU-Chat",
		"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 "Rahspide/MNN-Pocket-0.3B-RU-Chat" \
        --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": "Rahspide/MNN-Pocket-0.3B-RU-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with Ollama:
```
ollama run hf.co/Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M
```
Unsloth Desktop

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with Docker Model Runner:
```
docker model run hf.co/Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M
```

Lemonade

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Run and chat with the model

lemonade run user.MNN-Pocket-0.3B-RU-Chat-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

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 Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Rahspide/MNN-Pocket-0.3B-RU-Chat with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Rahspide/MNN-Pocket-0.3B-RU-Chat:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Rahspide commited on 1 day ago

Commit

afad59a

verified ·

1 Parent(s): 8bb6500

docs: honest evaluation section, official checkpoint degrades on Russian

Browse files

Files changed (1) hide show

README.md +24 -21

README.md CHANGED Viewed

@@ -141,28 +141,31 @@ table above.
 ## Evaluation
-60 held-out Russian prompts from the `saiga_scored` validation slice, greedy decoding, same template on both
-models. Answer A/B order is shuffled per prompt; the rating sheet and the key are separate files.
-| Automatic check | This model | `taobao-mnn/MNN-Pocket-0.3B` |
-|---|---|---|
-| answers in Russian (>50% Cyrillic) | **57 / 60** | 47 / 60 |
-| mean Cyrillic share of letters | **0.93** | 0.75 |
-| empty answers | 0 | 0 |
-| echoes the prompt | 2 | 0 |
-| mean answer length, words | 26.1 | 31.9 |
-| distinct-2 (higher = less repetition) | **0.90** | 0.82 |
-The Russian-language numbers are the point: the official checkpoint is zh/en-first and drifts out of Russian in
-13 of 60 cases, this one stays in Russian and repeats itself slightly less. It does echo the question twice,
-which the official model never does.
-Human rating is still open. The sheet is [`review/blind_sheet.md`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/review/blind_sheet.md),
-the key sits in the private run repo, and the raw answers are in `review/`. Rate 50–100 items on instruction
-following, naturalness, refusal and 2–3 turn coherence, then open the key.
-Still open: selective MERA tasks that fit a 0.3 B model, and a regression check against the continuation sister
-on Russian bits/char.
 ## Limitations

 ## Evaluation
+60 held-out Russian prompts from the `saiga_scored` validation slice, greedy decoding, the model's own template:
+| Automatic check | Result |
+|---|---|
+| answers in Russian (>50% Cyrillic) | 57 / 60 |
+| mean Cyrillic share of letters | 0.93 |
+| empty answers | 0 |
+| echoes the prompt | 2 |
+| mean answer length, words | 26.1 |
+| distinct-2 (higher = less repetition) | 0.90 |
+The sheet with all 60 prompts and answers is in
+[`review/blind_sheet.md`](https://huggingface.co/Rahspide/MNN-Pocket-0.3B-RU-Chat/blob/main/review/blind_sheet.md).
+Human rating on instruction following, naturalness, refusal and 2–3 turn coherence is still open.
+A comparison against `taobao-mnn/MNN-Pocket-0.3B` was attempted on the same prompts and dropped. That checkpoint
+degenerates on Russian input, repeating the prompt in bold markdown fragments:
+```
+Q: Как стать популярным в яндекс дзен?
+A: Конечный откорт: **"Популярный в яндекс дзен"** — это **не** в яндекс (в яндекс) — **в яндекс** — **в яндекс** — …
+```
+So it is not a baseline. A fair comparison needs the official checkpoint SFT-tuned on the same data, which is
+still open.
 ## Limitations