Instructions to use ericflo/Llama-3.1-SyntheticPython-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ericflo/Llama-3.1-SyntheticPython-8B-Base with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ericflo/Llama-3.1-SyntheticPython-8B-Base",
	filename="llama-3.1-syntheticpython-base_bf16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ericflo/Llama-3.1-SyntheticPython-8B-Base with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16
# Run inference directly in the terminal:
llama-cli -hf ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16
# Run inference directly in the terminal:
llama-cli -hf ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16

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 ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16
# Run inference directly in the terminal:
./llama-cli -hf ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16

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 ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16

Use Docker

docker model run hf.co/ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16

LM Studio
Jan
Ollama
How to use ericflo/Llama-3.1-SyntheticPython-8B-Base with Ollama:
```
ollama run hf.co/ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16
```

Unsloth Studio new

How to use ericflo/Llama-3.1-SyntheticPython-8B-Base with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ericflo/Llama-3.1-SyntheticPython-8B-Base to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ericflo/Llama-3.1-SyntheticPython-8B-Base to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ericflo/Llama-3.1-SyntheticPython-8B-Base to start chatting

Docker Model Runner
How to use ericflo/Llama-3.1-SyntheticPython-8B-Base with Docker Model Runner:
```
docker model run hf.co/ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16
```

Lemonade

How to use ericflo/Llama-3.1-SyntheticPython-8B-Base with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ericflo/Llama-3.1-SyntheticPython-8B-Base:BF16

Run and chat with the model

lemonade run user.Llama-3.1-SyntheticPython-8B-Base-BF16

List all available models

lemonade list

See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Meta-Llama-3.1-8B

model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: ericflo/SyntheticPython-Pretrain-v1
    type: completion
# max_steps: 200
# pretraining_dataset:
#   - path: ericflo/SyntheticPython-Pretrain-v1
#     name: default
#     type: pretrain
dataset_prepared_path: last_run_prepared2
val_set_size: 0.0
output_dir: ./outputs/model-out

sequence_len: 8192
sample_packing: false

wandb_project: syntheticpython
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch:
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

outputs/model-out

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 4

Training results

Framework versions

Transformers 4.44.0
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Downloads last month: 20

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ericflo/Llama-3.1-SyntheticPython-8B-Base

Base model

meta-llama/Llama-3.1-8B

Quantized

(324)

this model