Instructions to use tongliuphysics/Mistral-7B-Base-SFT-FocalPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tongliuphysics/Mistral-7B-Base-SFT-FocalPO with Transformers:

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

pipe = pipeline("text-generation", model="tongliuphysics/Mistral-7B-Base-SFT-FocalPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tongliuphysics/Mistral-7B-Base-SFT-FocalPO")
model = AutoModelForCausalLM.from_pretrained("tongliuphysics/Mistral-7B-Base-SFT-FocalPO")
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 tongliuphysics/Mistral-7B-Base-SFT-FocalPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tongliuphysics/Mistral-7B-Base-SFT-FocalPO

SGLang

How to use tongliuphysics/Mistral-7B-Base-SFT-FocalPO 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 "tongliuphysics/Mistral-7B-Base-SFT-FocalPO" \
    --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": "tongliuphysics/Mistral-7B-Base-SFT-FocalPO",
		"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 "tongliuphysics/Mistral-7B-Base-SFT-FocalPO" \
        --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": "tongliuphysics/Mistral-7B-Base-SFT-FocalPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tongliuphysics/Mistral-7B-Base-SFT-FocalPO with Docker Model Runner:
```
docker model run hf.co/tongliuphysics/Mistral-7B-Base-SFT-FocalPO
```

zephyr0-7b-ultra-p-0.05

This model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5029
Rewards/chosen: -1.1300
Rewards/rejected: -1.9954
Rewards/accuracies: 0.75
Rewards/margins: 0.8654
Logps/rejected: -427.3289
Logps/chosen: -335.3676
Logits/rejected: -1.9689
Logits/chosen: -2.0651

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-07
train_batch_size: 2
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.5625	0.2060	100	0.5413	-1.0460	-1.5393	0.6875	0.4932	-381.7129	-326.9707	-2.4726	-2.5375
0.5145	0.4119	200	0.5226	-1.0460	-1.7939	0.7656	0.7479	-407.1714	-326.9680	-2.1622	-2.2436
0.4948	0.6179	300	0.5165	-0.9692	-1.7757	0.75	0.8064	-405.3522	-319.2909	-2.0477	-2.1379
0.4931	0.8239	400	0.5051	-1.0779	-1.9119	0.75	0.8340	-418.9738	-330.1579	-2.0159	-2.1084

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.20.0

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for tongliuphysics/Mistral-7B-Base-SFT-FocalPO

Base model

mistralai/Mistral-7B-v0.1

Finetuned

HuggingFaceH4/mistral-7b-sft-beta

Finetuned

(153)

this model