Instructions to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WlappaAI/dracor-ru-split-small-lora_merged-GGUF", dtype="auto")

llama-cpp-python

How to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="WlappaAI/dracor-ru-split-small-lora_merged-GGUF",
	filename="dracor-ru-split-small-lora_merged.Q8_0.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 WlappaAI/dracor-ru-split-small-lora_merged-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0

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 WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0

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 WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0

Use Docker

docker model run hf.co/WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF with Ollama:
```
ollama run hf.co/WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0
```

Unsloth Studio new

How to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF 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 WlappaAI/dracor-ru-split-small-lora_merged-GGUF 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 WlappaAI/dracor-ru-split-small-lora_merged-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for WlappaAI/dracor-ru-split-small-lora_merged-GGUF to start chatting

Docker Model Runner
How to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF with Docker Model Runner:
```
docker model run hf.co/WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0
```

Lemonade

How to use WlappaAI/dracor-ru-split-small-lora_merged-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WlappaAI/dracor-ru-split-small-lora_merged-GGUF:Q8_0

Run and chat with the model

lemonade run user.dracor-ru-split-small-lora_merged-GGUF-Q8_0

List all available models

lemonade list

See axolotl config

axolotl version: 0.4.0

base_model: WlappaAI/Mistral-7B-wikipedia_ru_pruned-0.1_merged
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: ./datasets/ru-dracor
    type: completion
    field: text
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./models/output/dracor_ru_lora

adapter: lora
lora_model_dir:

sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 6
num_epochs: 1
optimizer: adamw_torch
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:
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 1
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

dracor-ru-small-lora_merged

This model is a Q8_0 GGUF merge of WlappaAI/dracor-ru-small-lora together with WlappaAI/Mistral-7B-wikipedia_ru_pruned-0.1_merged. It's trained on Russian DraCor dataset. It achieves the following results on the evaluation set:

Loss: 1.1876

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 6
eval_batch_size: 6
seed: 42
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

Training Loss	Epoch	Step	Validation Loss
1.7921	1.0	1056	1.6606

Framework versions

PEFT 0.10.0
Transformers 4.40.0.dev0
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.15.0
GGUF 0.9.0

Downloads last month: 5

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for WlappaAI/dracor-ru-split-small-lora_merged-GGUF

Base model

mistralai/Mistral-7B-v0.1

Finetuned

WlappaAI/Mistral-7B-wikipedia_ru_pruned-0.1_merged

Quantized

(2)

this model