Instructions to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "RantiRepo/Diploy_SFT_V1_2_qwen3_8B") - Transformers
How to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RantiRepo/Diploy_SFT_V1_2_qwen3_8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RantiRepo/Diploy_SFT_V1_2_qwen3_8B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RantiRepo/Diploy_SFT_V1_2_qwen3_8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RantiRepo/Diploy_SFT_V1_2_qwen3_8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RantiRepo/Diploy_SFT_V1_2_qwen3_8B
- SGLang
How to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B 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 "RantiRepo/Diploy_SFT_V1_2_qwen3_8B" \ --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": "RantiRepo/Diploy_SFT_V1_2_qwen3_8B", "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 "RantiRepo/Diploy_SFT_V1_2_qwen3_8B" \ --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": "RantiRepo/Diploy_SFT_V1_2_qwen3_8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Studio new
How to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for RantiRepo/Diploy_SFT_V1_2_qwen3_8B to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for RantiRepo/Diploy_SFT_V1_2_qwen3_8B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for RantiRepo/Diploy_SFT_V1_2_qwen3_8B to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="RantiRepo/Diploy_SFT_V1_2_qwen3_8B", max_seq_length=2048, ) - Docker Model Runner
How to use RantiRepo/Diploy_SFT_V1_2_qwen3_8B with Docker Model Runner:
docker model run hf.co/RantiRepo/Diploy_SFT_V1_2_qwen3_8B
| { | |
| "best_global_step": 900, | |
| "best_metric": 0.595556914806366, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/AITF_baseqwen3_8B_V1.2/checkpoint-900", | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 929, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021531422419593594, | |
| "grad_norm": 0.38749924302101135, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.7456, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04306284483918719, | |
| "grad_norm": 0.23645007610321045, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 1.2508, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06459426725878079, | |
| "grad_norm": 0.16630907356739044, | |
| "learning_rate": 0.0001999482703462211, | |
| "loss": 1.0123, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08612568967837438, | |
| "grad_norm": 0.1874742954969406, | |
| "learning_rate": 0.00019946334007549978, | |
| "loss": 0.9242, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10765711209796797, | |
| "grad_norm": 0.1982610672712326, | |
| "learning_rate": 0.0001984704140331751, | |
| "loss": 0.8479, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10765711209796797, | |
| "eval_loss": 0.7989935874938965, | |
| "eval_runtime": 368.247, | |
| "eval_samples_per_second": 10.105, | |
| "eval_steps_per_second": 2.528, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12918853451756157, | |
| "grad_norm": 0.2351531982421875, | |
| "learning_rate": 0.0001969745634568572, | |
| "loss": 0.8075, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15071995693715515, | |
| "grad_norm": 0.2675715982913971, | |
| "learning_rate": 0.00019498342820427794, | |
| "loss": 0.8, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17225137935674875, | |
| "grad_norm": 0.2564864754676819, | |
| "learning_rate": 0.00019250717773373462, | |
| "loss": 0.7552, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.19378280177634236, | |
| "grad_norm": 0.28067538142204285, | |
| "learning_rate": 0.0001895584591649349, | |
| "loss": 0.7529, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.21531422419593593, | |
| "grad_norm": 0.25266703963279724, | |
| "learning_rate": 0.00018615233268551643, | |
| "loss": 0.727, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21531422419593593, | |
| "eval_loss": 0.7019057869911194, | |
| "eval_runtime": 367.354, | |
| "eval_samples_per_second": 10.129, | |
| "eval_steps_per_second": 2.534, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23684564661552954, | |
| "grad_norm": 0.2786823809146881, | |
| "learning_rate": 0.00018230619463314266, | |
| "loss": 0.7363, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.25837706903512314, | |
| "grad_norm": 0.2877826690673828, | |
| "learning_rate": 0.0001780396886460237, | |
| "loss": 0.7094, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.27990849145471675, | |
| "grad_norm": 0.3062780499458313, | |
| "learning_rate": 0.00017337460533564845, | |
| "loss": 0.7013, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3014399138743103, | |
| "grad_norm": 0.29140764474868774, | |
| "learning_rate": 0.0001683347709941367, | |
| "loss": 0.6772, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3229713362939039, | |
| "grad_norm": 0.2650732398033142, | |
| "learning_rate": 0.00016294592590462316, | |
| "loss": 0.6896, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3229713362939039, | |
| "eval_loss": 0.6610061526298523, | |
| "eval_runtime": 367.3279, | |
| "eval_samples_per_second": 10.13, | |
| "eval_steps_per_second": 2.535, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3445027587134975, | |
| "grad_norm": 0.2866383194923401, | |
| "learning_rate": 0.00015723559287618728, | |
| "loss": 0.6685, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3660341811330911, | |
| "grad_norm": 0.2941460609436035, | |
| "learning_rate": 0.00015123293667476887, | |
| "loss": 0.6743, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3875656035526847, | |
| "grad_norm": 0.2664410471916199, | |
| "learning_rate": 0.00014496861506800758, | |
| "loss": 0.6755, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4090970259722783, | |
| "grad_norm": 0.2797100245952606, | |
| "learning_rate": 0.00013847462224477538, | |
| "loss": 0.6691, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.43062844839187187, | |
| "grad_norm": 0.30962368845939636, | |
| "learning_rate": 0.00013178412540911457, | |
| "loss": 0.6658, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43062844839187187, | |
| "eval_loss": 0.6373162865638733, | |
| "eval_runtime": 367.4733, | |
| "eval_samples_per_second": 10.126, | |
| "eval_steps_per_second": 2.534, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.45215987081146547, | |
| "grad_norm": 0.29752910137176514, | |
| "learning_rate": 0.00012493129538315788, | |
| "loss": 0.6587, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4736912932310591, | |
| "grad_norm": 0.304659903049469, | |
| "learning_rate": 0.00011795113208420208, | |
| "loss": 0.6466, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4952227156506527, | |
| "grad_norm": 0.3261611759662628, | |
| "learning_rate": 0.00011087928576728865, | |
| "loss": 0.6216, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5167541380702463, | |
| "grad_norm": 0.3342382311820984, | |
| "learning_rate": 0.00010375187494627098, | |
| "loss": 0.6435, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5382855604898399, | |
| "grad_norm": 0.2871527075767517, | |
| "learning_rate": 9.660530192331191e-05, | |
| "loss": 0.643, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5382855604898399, | |
| "eval_loss": 0.6207689642906189, | |
| "eval_runtime": 367.6602, | |
| "eval_samples_per_second": 10.121, | |
| "eval_steps_per_second": 2.532, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5598169829094335, | |
| "grad_norm": 0.3142107129096985, | |
| "learning_rate": 8.947606686897045e-05, | |
| "loss": 0.6355, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5813484053290271, | |
| "grad_norm": 0.3034207820892334, | |
| "learning_rate": 8.240058140243834e-05, | |
| "loss": 0.639, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6028798277486206, | |
| "grad_norm": 0.2917335033416748, | |
| "learning_rate": 7.541498262404125e-05, | |
| "loss": 0.6345, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6244112501682142, | |
| "grad_norm": 0.301921010017395, | |
| "learning_rate": 6.855494854980857e-05, | |
| "loss": 0.6361, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6459426725878078, | |
| "grad_norm": 0.2999766170978546, | |
| "learning_rate": 6.185551589075482e-05, | |
| "loss": 0.6266, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6459426725878078, | |
| "eval_loss": 0.6095116138458252, | |
| "eval_runtime": 369.6908, | |
| "eval_samples_per_second": 10.065, | |
| "eval_steps_per_second": 2.518, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6674740950074014, | |
| "grad_norm": 0.2857365310192108, | |
| "learning_rate": 5.535090110754131e-05, | |
| "loss": 0.6379, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.689005517426995, | |
| "grad_norm": 0.2973370850086212, | |
| "learning_rate": 4.9074325654457446e-05, | |
| "loss": 0.6126, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7105369398465886, | |
| "grad_norm": 0.3231595754623413, | |
| "learning_rate": 4.305784630526416e-05, | |
| "loss": 0.6105, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7320683622661822, | |
| "grad_norm": 0.2923620939254761, | |
| "learning_rate": 3.7332191427488784e-05, | |
| "loss": 0.6266, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7535997846857758, | |
| "grad_norm": 0.32130059599876404, | |
| "learning_rate": 3.192660404137729e-05, | |
| "loss": 0.6088, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7535997846857758, | |
| "eval_loss": 0.6016086935997009, | |
| "eval_runtime": 367.7262, | |
| "eval_samples_per_second": 10.119, | |
| "eval_steps_per_second": 2.532, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7751312071053694, | |
| "grad_norm": 0.2963238060474396, | |
| "learning_rate": 2.6868692465060828e-05, | |
| "loss": 0.6256, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.796662629524963, | |
| "grad_norm": 0.2954428195953369, | |
| "learning_rate": 2.2184289308744844e-05, | |
| "loss": 0.6201, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8181940519445566, | |
| "grad_norm": 0.3122366964817047, | |
| "learning_rate": 1.7897319538090962e-05, | |
| "loss": 0.6164, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8397254743641501, | |
| "grad_norm": 0.3299662470817566, | |
| "learning_rate": 1.402967828063897e-05, | |
| "loss": 0.6026, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8612568967837437, | |
| "grad_norm": 0.2979361414909363, | |
| "learning_rate": 1.0601118999356907e-05, | |
| "loss": 0.6103, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8612568967837437, | |
| "eval_loss": 0.596613347530365, | |
| "eval_runtime": 367.8439, | |
| "eval_samples_per_second": 10.116, | |
| "eval_steps_per_second": 2.531, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8827883192033373, | |
| "grad_norm": 0.3615986108779907, | |
| "learning_rate": 7.629152604458156e-06, | |
| "loss": 0.6052, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.9043197416229309, | |
| "grad_norm": 0.31248706579208374, | |
| "learning_rate": 5.128958018758012e-06, | |
| "loss": 0.5928, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9258511640425245, | |
| "grad_norm": 0.3367156982421875, | |
| "learning_rate": 3.1133046533455947e-06, | |
| "loss": 0.6049, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.9473825864621181, | |
| "grad_norm": 0.28718671202659607, | |
| "learning_rate": 1.592487189516212e-06, | |
| "loss": 0.6053, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.9689140088817118, | |
| "grad_norm": 0.32894209027290344, | |
| "learning_rate": 5.742730000568908e-07, | |
| "loss": 0.6172, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9689140088817118, | |
| "eval_loss": 0.595556914806366, | |
| "eval_runtime": 367.6823, | |
| "eval_samples_per_second": 10.12, | |
| "eval_steps_per_second": 2.532, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9904454313013054, | |
| "grad_norm": 0.34396475553512573, | |
| "learning_rate": 6.386247842353754e-08, | |
| "loss": 0.6045, | |
| "step": 920 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 929, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2554944340455096e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |