Instructions to use advy/llama71b-mentalchat16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use advy/llama71b-mentalchat16k with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-70B-Instruct")
model = PeftModel.from_pretrained(base_model, "advy/llama71b-mentalchat16k")

Transformers

How to use advy/llama71b-mentalchat16k with Transformers:

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

pipe = pipeline("text-generation", model="advy/llama71b-mentalchat16k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("advy/llama71b-mentalchat16k", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use advy/llama71b-mentalchat16k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "advy/llama71b-mentalchat16k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "advy/llama71b-mentalchat16k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/advy/llama71b-mentalchat16k

SGLang

How to use advy/llama71b-mentalchat16k 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 "advy/llama71b-mentalchat16k" \
    --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": "advy/llama71b-mentalchat16k",
		"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 "advy/llama71b-mentalchat16k" \
        --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": "advy/llama71b-mentalchat16k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use advy/llama71b-mentalchat16k with Docker Model Runner:
```
docker model run hf.co/advy/llama71b-mentalchat16k
```

llama71b-mentalchat16k

This model is a fine-tuned version of meta-llama/Llama-3.1-70B-Instruct on the ShenLab/MentalChat16k dataset. It achieves the following results on the evaluation set:

Loss: 0.6542

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: 8e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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: 0.03
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8207	0.1496	100	0.7920
0.7716	0.2992	200	0.7492
0.7208	0.4488	300	0.7363
0.7237	0.5985	400	0.7187
0.7156	0.7481	500	0.7088
0.7024	0.8977	600	0.6963
0.6125	1.0464	700	0.7004
0.5753	1.1960	800	0.6942
0.5497	1.3456	900	0.6878
0.5589	1.4952	1000	0.6804
0.5453	1.6448	1100	0.6761
0.5316	1.7945	1200	0.6693
0.5422	1.9441	1300	0.6634
0.349	2.0928	1400	0.7011
0.3481	2.2424	1500	0.7033
0.337	2.3920	1600	0.7048
0.3505	2.5416	1700	0.7049
0.3424	2.6912	1800	0.7052

LLAMA 3.1 TEST SET EVALUATION:

================================================== ROUGE Scores (Average F-Measure):

ROUGE-1: 0.3051
ROUGE-2: 0.1122
ROUGE-L: 0.1678

BLEU Score: - BLEU: 0.0646

Framework versions

PEFT 0.18.0
Transformers 4.57.1
Pytorch 2.5.1+cu124
Datasets 4.4.1
Tokenizers 0.22.1

Downloads last month: 3

Model tree for advy/llama71b-mentalchat16k

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Adapter

(103)

this model

advy
/

llama71b-mentalchat16k

llama71b-mentalchat16k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

BLEU Score: - BLEU: 0.0646

Framework versions

Model tree for advy/llama71b-mentalchat16k

Dataset used to train advy/llama71b-mentalchat16k