Instructions to use wndknd/codellama-7b-stata-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wndknd/codellama-7b-stata-instruct with Transformers:

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

pipe = pipeline("text-generation", model="wndknd/codellama-7b-stata-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wndknd/codellama-7b-stata-instruct")
model = AutoModelForCausalLM.from_pretrained("wndknd/codellama-7b-stata-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use wndknd/codellama-7b-stata-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wndknd/codellama-7b-stata-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wndknd/codellama-7b-stata-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wndknd/codellama-7b-stata-instruct

SGLang

How to use wndknd/codellama-7b-stata-instruct 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 "wndknd/codellama-7b-stata-instruct" \
    --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": "wndknd/codellama-7b-stata-instruct",
		"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 "wndknd/codellama-7b-stata-instruct" \
        --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": "wndknd/codellama-7b-stata-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wndknd/codellama-7b-stata-instruct with Docker Model Runner:
```
docker model run hf.co/wndknd/codellama-7b-stata-instruct
```

See axolotl config

axolotl version: 0.4.0

base_model: wndknd/codellama-7b-stata
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: HuggingFaceH4/CodeAlpaca_20K
    type:
      field_instruction: prompt
      field_output: completion
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

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

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
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
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true

warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: #deepspeed_configs/zero2.json # multi-gpu only
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:

out

This model is a fine-tuned version of wndknd/codellama-7b-stata on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5586

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: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.1853	0.0	1	1.0273
0.6457	0.25	104	0.6773
0.6475	0.5	208	0.6700
0.5701	0.75	312	0.5586

Framework versions

Transformers 4.37.0
Pytorch 2.1.1+cu121
Datasets 2.16.1
Tokenizers 0.15.0

Downloads last month: 6

Model tree for wndknd/codellama-7b-stata-instruct

Base model

wndknd/codellama-7b-stata

Finetuned

(1)

this model