Instructions to use neph1/llama-3.1-instruct-bellman-8b-swedish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neph1/llama-3.1-instruct-bellman-8b-swedish with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("neph1/llama-3.1-instruct-bellman-8b-swedish", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use neph1/llama-3.1-instruct-bellman-8b-swedish 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 neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M

Use Docker

docker model run hf.co/neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M

LM Studio
Jan
Ollama
How to use neph1/llama-3.1-instruct-bellman-8b-swedish with Ollama:
```
ollama run hf.co/neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M
```
Unsloth Desktop
Docker Model Runner
How to use neph1/llama-3.1-instruct-bellman-8b-swedish with Docker Model Runner:
```
docker model run hf.co/neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M
```

Lemonade

How to use neph1/llama-3.1-instruct-bellman-8b-swedish with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neph1/llama-3.1-instruct-bellman-8b-swedish:Q3_K_M

Run and chat with the model

lemonade run user.llama-3.1-instruct-bellman-8b-swedish-Q3_K_M

List all available models

lemonade list

Atomic Chat

Model Card for Bellman

This version of bellman is finetuned from llama-3.1-instruct-8b. It's finetuned for prompt question answering, based on a dataset created from Swedish wikipedia, with a lot of Sweden-centric questions. New from previous versions is questions from a translated code-feedback dataset, as well as a number of stories. It's not great at generating stories, but better than previosly.

Try out the Q8 version here: https://huggingface.co/spaces/neph1/bellman (cpu)

Model Details

Training run on 240724:

Step Training Loss Validation Loss
25 1.352200 1.034565
50 1.033600 1.009348
75 1.022400 0.996665
100 1.002900 0.988050
125 1.014600 0.981633
150 1.006300 0.975584
175 0.988800 0.970966
200 0.985300 0.967037
225 0.992400 0.964120
250 0.950000 0.962472
275 0.931000 0.960848
300 0.932000 0.958946 <-- picked checkpoint

Training Parameters

per_device_train_batch_size = 4,
gradient_accumulation_steps = 16,
num_train_epochs=3,
warmup_steps = 5,
learning_rate = 3e-5,
logging_steps = 25,
optim = "adamw_8bit",
weight_decay = 0.01,
lr_scheduler_type = "linear",
seed = 3407,
per_device_eval_batch_size = 2,
eval_strategy="steps",
eval_accumulation_steps = 32,
eval_steps = 25,
eval_delay = 0,
save_strategy="steps",
save_steps=50,