Instructions to use esha111/recipe-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use esha111/recipe-generator with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")
model = PeftModel.from_pretrained(base_model, "esha111/recipe-generator")

llama-cpp-python

How to use esha111/recipe-generator with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="esha111/recipe-generator",
	filename="model-f16.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 esha111/recipe-generator with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf esha111/recipe-generator:F16
# Run inference directly in the terminal:
llama-cli -hf esha111/recipe-generator:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf esha111/recipe-generator:F16
# Run inference directly in the terminal:
llama-cli -hf esha111/recipe-generator:F16

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 esha111/recipe-generator:F16
# Run inference directly in the terminal:
./llama-cli -hf esha111/recipe-generator:F16

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 esha111/recipe-generator:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf esha111/recipe-generator:F16

Use Docker

docker model run hf.co/esha111/recipe-generator:F16

LM Studio
Jan

vLLM

How to use esha111/recipe-generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "esha111/recipe-generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "esha111/recipe-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/esha111/recipe-generator:F16

Ollama
How to use esha111/recipe-generator with Ollama:
```
ollama run hf.co/esha111/recipe-generator:F16
```

Unsloth Studio new

How to use esha111/recipe-generator 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 esha111/recipe-generator 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 esha111/recipe-generator to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for esha111/recipe-generator to start chatting

Docker Model Runner
How to use esha111/recipe-generator with Docker Model Runner:
```
docker model run hf.co/esha111/recipe-generator:F16
```

Lemonade

How to use esha111/recipe-generator with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull esha111/recipe-generator:F16

Run and chat with the model

lemonade run user.recipe-generator-F16

List all available models

lemonade list

See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Meta-Llama-3-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  # This will be the path used for the data when it is saved to the Volume in the cloud.
  - path: "data/recipe_training_dataset.jsonl"
    ds_type: "json"
    type:
      # JSONL file contains question, context, answer fields per line.
      # This gets mapped to instruction, input, output axolotl tags.
      field_instruction: system
      field_input: user
      field_output: assistant
      # Format is used by axolotl to generate the prompt.
      format: |-
       {instruction} 
       {input}
dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_32bit
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: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

hub_model_id: esha111/recipe-generator

recipe-generator

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B 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
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1

Training results

Framework versions

PEFT 0.11.1
Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 6

GGUF

Model size

0 params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Model tree for esha111/recipe-generator

Base model

meta-llama/Meta-Llama-3-8B

Adapter

(723)

this model

esha111
/

recipe-generator

recipe-generator

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for esha111/recipe-generator

Spaces using esha111/recipe-generator 2