Instructions to use dty1aaa/codellama-7b-instruct-hf-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dty1aaa/codellama-7b-instruct-hf-sft with Transformers:

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

pipe = pipeline("text-generation", model="dty1aaa/codellama-7b-instruct-hf-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dty1aaa/codellama-7b-instruct-hf-sft")
model = AutoModelForCausalLM.from_pretrained("dty1aaa/codellama-7b-instruct-hf-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dty1aaa/codellama-7b-instruct-hf-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dty1aaa/codellama-7b-instruct-hf-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dty1aaa/codellama-7b-instruct-hf-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dty1aaa/codellama-7b-instruct-hf-sft

SGLang

How to use dty1aaa/codellama-7b-instruct-hf-sft 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 "dty1aaa/codellama-7b-instruct-hf-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dty1aaa/codellama-7b-instruct-hf-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "dty1aaa/codellama-7b-instruct-hf-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dty1aaa/codellama-7b-instruct-hf-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dty1aaa/codellama-7b-instruct-hf-sft with Docker Model Runner:
```
docker model run hf.co/dty1aaa/codellama-7b-instruct-hf-sft
```

codellama-7b-instruct-hf-sft / README.md

dty1aaa

Update README.md

d4b8df7 verified about 2 months ago

preview code

raw

history blame contribute delete

2.12 kB

	---
	library_name: transformers
	license: other
	base_model: codellama/CodeLlama-7b-Instruct-hf
	tags:
	- llama-factory
	- full
	- generated_from_trainer
	model-index:
	- name: final_sft_CodeLlama-7b-Instruct-hf
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# final_sft_CodeLlama-7b-Instruct-hf

	This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the efficoder dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.3331

	## Model description

	train on EFFIINSTRUCT_python

	## Intended uses & limitations

	generate effective code

	## Training and evaluation data

	train on EFFIINSTRUCT_python

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 5e-06
	- train_batch_size: 8
	- eval_batch_size: 1
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 4
	- gradient_accumulation_steps: 2
	- total_train_batch_size: 64
	- total_eval_batch_size: 4
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_ratio: 0.03
	- num_epochs: 4.0

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 0.2475 \| 0.3401 \| 50 \| 0.2433 \|
	\| 0.2425 \| 0.6803 \| 100 \| 0.2314 \|
	\| 0.2147 \| 1.0204 \| 150 \| 0.2318 \|
	\| 0.1702 \| 1.3605 \| 200 \| 0.2378 \|
	\| 0.1758 \| 1.7007 \| 250 \| 0.2396 \|
	\| 0.1438 \| 2.0408 \| 300 \| 0.2643 \|
	\| 0.0989 \| 2.3810 \| 350 \| 0.2823 \|
	\| 0.0991 \| 2.7211 \| 400 \| 0.2799 \|
	\| 0.065 \| 3.0612 \| 450 \| 0.3123 \|
	\| 0.0601 \| 3.4014 \| 500 \| 0.3348 \|
	\| 0.0645 \| 3.7415 \| 550 \| 0.3324 \|


	### Framework versions

	- Transformers 4.44.2
	- Pytorch 2.2.2+cu121
	- Datasets 4.8.4
	- Tokenizers 0.19.1