Instructions to use Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 with Transformers:

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

pipe = pipeline("text-generation", model="Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1")
model = AutoModelForCausalLM.from_pretrained("Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1

SGLang

How to use Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 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 "Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 with Docker Model Runner:
```
docker model run hf.co/Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1
```

See axolotl config

axolotl version: 0.3.0

base_model: Locutusque/TinyMistral-248M-v2.5
model_type: MistralForCausalLM
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

dataset_processes: 20

datasets:
  - path: epfl-llm/guidelines
    type: completion
    field: clean_text
  - path: JeanKaddour/minipile
    type: completion
    field: text
  
dataset_prepared_path: TinyMistral-FFT-data
val_set_size: 0.001
output_dir: ./TinyMistral-FFT

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

# wandb configuration
wandb_project: TinyMistral-FFT
wandb_watch:
wandb_run_id:
wandb_log_model: 

gradient_accumulation_steps: 2
micro_batch_size: 4
num_epochs: 1
optimizer: paged_adamw_32bit
lr_scheduler: constant
cosine_min_lr_ratio: 

learning_rate: 0.00005

train_on_inputs: true
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
auto_resume_from_checkpoints: True
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true

warmup_steps: 10
evals_per_epoch: 100
# eval_steps: 10
eval_table_size:
saves_per_epoch: 50
debug:
deepspeed: #deepspeed/zero2.json # multi-gpu only
weight_decay: 0

# tokens:


special_tokens:
  bos_token: "<|bos|>"
  eos_token: "<|endoftext|>"
  unk_token: "<unk>"

TinyMistral-StructureEvaluator

This model was further trained on the epfl-llm/guidelines and JeanKaddour/minipile datasets for 1 epoch.

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
training_steps: 197279

Training results

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 6

Model tree for Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1

Base model

Locutusque/TinyMistral-248M-v2.5

Finetuned

(3)

this model

Finetunes

1 model

Dans-DiscountModels
/

TinyMistral-v2.5-MiniPile-Guidelines-E1

TinyMistral-StructureEvaluator

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1

Datasets used to train Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1