Instructions to use rbelanec/train_conala_123_1760637668 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_conala_123_1760637668 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "rbelanec/train_conala_123_1760637668")

Transformers

How to use rbelanec/train_conala_123_1760637668 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_conala_123_1760637668")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_conala_123_1760637668", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_conala_123_1760637668 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_conala_123_1760637668"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_conala_123_1760637668",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_conala_123_1760637668

SGLang

How to use rbelanec/train_conala_123_1760637668 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 "rbelanec/train_conala_123_1760637668" \
    --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": "rbelanec/train_conala_123_1760637668",
		"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 "rbelanec/train_conala_123_1760637668" \
        --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": "rbelanec/train_conala_123_1760637668",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_conala_123_1760637668 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_conala_123_1760637668
```

train_conala_123_1760637668

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the conala dataset. It achieves the following results on the evaluation set:

Loss: 0.6767
Num Input Tokens Seen: 3047552

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: 123
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
2.7358	1.0	536	2.1967	152672
1.261	2.0	1072	1.0879	305288
0.758	3.0	1608	0.9051	457952
0.5597	4.0	2144	0.8311	610944
1.1423	5.0	2680	0.7915	762440
0.7895	6.0	3216	0.7657	914920
0.5906	7.0	3752	0.7451	1067520
0.7893	8.0	4288	0.7291	1220200
0.919	9.0	4824	0.7161	1372560
0.4873	10.0	5360	0.7068	1524216
0.8047	11.0	5896	0.6995	1675880
0.7024	12.0	6432	0.6918	1828344
0.845	13.0	6968	0.6872	1980376
0.5402	14.0	7504	0.6830	2132544
0.5934	15.0	8040	0.6805	2284440
0.5969	16.0	8576	0.6789	2436520
0.4848	17.0	9112	0.6784	2589096
0.7806	18.0	9648	0.6770	2741936
0.6403	19.0	10184	0.6768	2894976
0.8095	20.0	10720	0.6767	3047552

Framework versions

PEFT 0.17.1
Transformers 4.51.3
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for rbelanec/train_conala_123_1760637668

Base model

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

Adapter

(2405)

this model