Instructions to use tsavage68/Na_M2_1000steps_1e6rate_SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tsavage68/Na_M2_1000steps_1e6rate_SFT with Transformers:

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

pipe = pipeline("text-generation", model="tsavage68/Na_M2_1000steps_1e6rate_SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tsavage68/Na_M2_1000steps_1e6rate_SFT")
model = AutoModelForCausalLM.from_pretrained("tsavage68/Na_M2_1000steps_1e6rate_SFT", device_map="auto")
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 Settings

vLLM

How to use tsavage68/Na_M2_1000steps_1e6rate_SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tsavage68/Na_M2_1000steps_1e6rate_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": "tsavage68/Na_M2_1000steps_1e6rate_SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tsavage68/Na_M2_1000steps_1e6rate_SFT

SGLang

How to use tsavage68/Na_M2_1000steps_1e6rate_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 "tsavage68/Na_M2_1000steps_1e6rate_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": "tsavage68/Na_M2_1000steps_1e6rate_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 "tsavage68/Na_M2_1000steps_1e6rate_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": "tsavage68/Na_M2_1000steps_1e6rate_SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tsavage68/Na_M2_1000steps_1e6rate_SFT with Docker Model Runner:
```
docker model run hf.co/tsavage68/Na_M2_1000steps_1e6rate_SFT
```

Na_M2_1000steps_1e6rate_SFT

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1550

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: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
0.349	0.2667	50	0.3425
0.2797	0.5333	100	0.2671
0.1882	0.8	150	0.1831
0.1593	1.0667	200	0.1748
0.1609	1.3333	250	0.1586
0.1544	1.6	300	0.1575
0.1558	1.8667	350	0.1564
0.1524	2.1333	400	0.1574
0.1527	2.4	450	0.1568
0.1564	2.6667	500	0.1554
0.1523	2.9333	550	0.1563
0.1519	3.2	600	0.1558
0.1532	3.4667	650	0.1555
0.1508	3.7333	700	0.1549
0.1518	4.0	750	0.1550
0.1507	4.2667	800	0.1551
0.1501	4.5333	850	0.1550
0.1477	4.8	900	0.1549
0.1464	5.0667	950	0.1550
0.1488	5.3333	1000	0.1550

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Downloads last month: 7

Safetensors

Model size

7B params

Tensor type

F16

Model tree for tsavage68/Na_M2_1000steps_1e6rate_SFT

Base model

mistralai/Mistral-7B-Instruct-v0.2

Finetuned

(1097)

this model