Instructions to use tsavage68/chat_200STEPS_1e6_01beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tsavage68/chat_200STEPS_1e6_01beta with Transformers:

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

pipe = pipeline("text-generation", model="tsavage68/chat_200STEPS_1e6_01beta")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tsavage68/chat_200STEPS_1e6_01beta")
model = AutoModelForCausalLM.from_pretrained("tsavage68/chat_200STEPS_1e6_01beta", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tsavage68/chat_200STEPS_1e6_01beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tsavage68/chat_200STEPS_1e6_01beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tsavage68/chat_200STEPS_1e6_01beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tsavage68/chat_200STEPS_1e6_01beta

SGLang

How to use tsavage68/chat_200STEPS_1e6_01beta 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 "tsavage68/chat_200STEPS_1e6_01beta" \
    --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": "tsavage68/chat_200STEPS_1e6_01beta",
		"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 "tsavage68/chat_200STEPS_1e6_01beta" \
        --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": "tsavage68/chat_200STEPS_1e6_01beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tsavage68/chat_200STEPS_1e6_01beta with Docker Model Runner:
```
docker model run hf.co/tsavage68/chat_200STEPS_1e6_01beta
```

chat_200STEPS_1e6_01beta

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6840
Rewards/chosen: -0.0632
Rewards/rejected: -0.0877
Rewards/accuracies: 0.4637
Rewards/margins: 0.0245
Logps/rejected: -19.6678
Logps/chosen: -17.3765
Logits/rejected: -0.6331
Logits/chosen: -0.6330

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: 1e-06
train_batch_size: 4
eval_batch_size: 1
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: cosine
lr_scheduler_warmup_steps: 100
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6939	0.1	50	0.6917	-0.0037	-0.0069	0.4901	0.0032	-18.8600	-16.7813	-0.5975	-0.5973
0.6902	0.2	100	0.6919	-0.1261	-0.1323	0.4440	0.0063	-20.1147	-18.0054	-0.6143	-0.6142
0.691	0.29	150	0.6846	-0.0911	-0.1153	0.4615	0.0242	-19.9439	-17.6551	-0.6419	-0.6418
0.6838	0.39	200	0.6840	-0.0632	-0.0877	0.4637	0.0245	-19.6678	-17.3765	-0.6331	-0.6330

Framework versions

Transformers 4.37.2
Pytorch 2.0.0+cu117
Datasets 2.17.0
Tokenizers 0.15.2

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

F16

Model tree for tsavage68/chat_200STEPS_1e6_01beta

Base model

meta-llama/Llama-2-7b-chat-hf

Finetuned

(552)

this model