Instructions to use thanaphatt1/qwen3.5-9b-muspsy-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use thanaphatt1/qwen3.5-9b-muspsy-fixed with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B") model = PeftModel.from_pretrained(base_model, "thanaphatt1/qwen3.5-9b-muspsy-fixed") - Transformers
How to use thanaphatt1/qwen3.5-9b-muspsy-fixed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="thanaphatt1/qwen3.5-9b-muspsy-fixed") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("thanaphatt1/qwen3.5-9b-muspsy-fixed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use thanaphatt1/qwen3.5-9b-muspsy-fixed with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thanaphatt1/qwen3.5-9b-muspsy-fixed" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thanaphatt1/qwen3.5-9b-muspsy-fixed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/thanaphatt1/qwen3.5-9b-muspsy-fixed
- SGLang
How to use thanaphatt1/qwen3.5-9b-muspsy-fixed 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 "thanaphatt1/qwen3.5-9b-muspsy-fixed" \ --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": "thanaphatt1/qwen3.5-9b-muspsy-fixed", "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 "thanaphatt1/qwen3.5-9b-muspsy-fixed" \ --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": "thanaphatt1/qwen3.5-9b-muspsy-fixed", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use thanaphatt1/qwen3.5-9b-muspsy-fixed with Docker Model Runner:
docker model run hf.co/thanaphatt1/qwen3.5-9b-muspsy-fixed
Training in progress, step 3831
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +35 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346302176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53189e217385ca6c5b02b8ca68af2b15180a111c4ee2f3ff44bac343cd388372
|
| 3 |
size 346302176
|
trainer_log.jsonl
CHANGED
|
@@ -355,3 +355,38 @@
|
|
| 355 |
{"current_steps": 3490, "total_steps": 3831, "loss": 1.1492552757263184, "lr": 4.818594191922576e-06, "epoch": 2.73314730503745, "percentage": 91.1, "elapsed_time": "22:06:23", "remaining_time": "2:09:35"}
|
| 356 |
{"current_steps": 3500, "total_steps": 3831, "loss": 1.1195759773254395, "lr": 4.543047174006209e-06, "epoch": 2.7409800753904148, "percentage": 91.36, "elapsed_time": "22:10:12", "remaining_time": "2:05:47"}
|
| 357 |
{"current_steps": 3500, "total_steps": 3831, "eval_loss": 1.2651914358139038, "epoch": 2.7409800753904148, "percentage": 91.36, "elapsed_time": "22:15:38", "remaining_time": "2:06:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 355 |
{"current_steps": 3490, "total_steps": 3831, "loss": 1.1492552757263184, "lr": 4.818594191922576e-06, "epoch": 2.73314730503745, "percentage": 91.1, "elapsed_time": "22:06:23", "remaining_time": "2:09:35"}
|
| 356 |
{"current_steps": 3500, "total_steps": 3831, "loss": 1.1195759773254395, "lr": 4.543047174006209e-06, "epoch": 2.7409800753904148, "percentage": 91.36, "elapsed_time": "22:10:12", "remaining_time": "2:05:47"}
|
| 357 |
{"current_steps": 3500, "total_steps": 3831, "eval_loss": 1.2651914358139038, "epoch": 2.7409800753904148, "percentage": 91.36, "elapsed_time": "22:15:38", "remaining_time": "2:06:18"}
|
| 358 |
+
{"current_steps": 3510, "total_steps": 3831, "loss": 1.1164446830749513, "lr": 4.275429216726201e-06, "epoch": 2.748812845743379, "percentage": 91.62, "elapsed_time": "22:19:26", "remaining_time": "2:02:29"}
|
| 359 |
+
{"current_steps": 3520, "total_steps": 3831, "loss": 1.0795605659484864, "lr": 4.015762549568724e-06, "epoch": 2.756645616096343, "percentage": 91.88, "elapsed_time": "22:23:07", "remaining_time": "1:58:40"}
|
| 360 |
+
{"current_steps": 3530, "total_steps": 3831, "loss": 1.0812619209289551, "lr": 3.7640687415519293e-06, "epoch": 2.764478386449307, "percentage": 92.14, "elapsed_time": "22:26:48", "remaining_time": "1:54:50"}
|
| 361 |
+
{"current_steps": 3540, "total_steps": 3831, "loss": 1.1149346351623535, "lr": 3.520368699434384e-06, "epoch": 2.7723111568022714, "percentage": 92.4, "elapsed_time": "22:30:29", "remaining_time": "1:51:00"}
|
| 362 |
+
{"current_steps": 3550, "total_steps": 3831, "loss": 1.099393367767334, "lr": 3.2846826659784334e-06, "epoch": 2.780143927155236, "percentage": 92.67, "elapsed_time": "22:34:10", "remaining_time": "1:47:11"}
|
| 363 |
+
{"current_steps": 3560, "total_steps": 3831, "loss": 1.1055167198181153, "lr": 3.057030218268764e-06, "epoch": 2.7879766975082, "percentage": 92.93, "elapsed_time": "22:37:46", "remaining_time": "1:43:21"}
|
| 364 |
+
{"current_steps": 3570, "total_steps": 3831, "loss": 1.1351775169372558, "lr": 2.8374302660862826e-06, "epoch": 2.7958094678611642, "percentage": 93.19, "elapsed_time": "22:41:35", "remaining_time": "1:39:32"}
|
| 365 |
+
{"current_steps": 3580, "total_steps": 3831, "loss": 1.0925300598144532, "lr": 2.6259010503373206e-06, "epoch": 2.8036422382141284, "percentage": 93.45, "elapsed_time": "22:45:18", "remaining_time": "1:35:43"}
|
| 366 |
+
{"current_steps": 3590, "total_steps": 3831, "loss": 1.0652141571044922, "lr": 2.4224601415385294e-06, "epoch": 2.8114750085670925, "percentage": 93.71, "elapsed_time": "22:48:59", "remaining_time": "1:31:54"}
|
| 367 |
+
{"current_steps": 3600, "total_steps": 3831, "loss": 1.1031173706054687, "lr": 2.227124438357353e-06, "epoch": 2.8193077789200567, "percentage": 93.97, "elapsed_time": "22:52:39", "remaining_time": "1:28:04"}
|
| 368 |
+
{"current_steps": 3610, "total_steps": 3831, "loss": 1.1134588241577148, "lr": 2.0399101662083807e-06, "epoch": 2.827140549273021, "percentage": 94.23, "elapsed_time": "22:56:19", "remaining_time": "1:24:15"}
|
| 369 |
+
{"current_steps": 3620, "total_steps": 3831, "loss": 1.094143009185791, "lr": 1.8608328759055716e-06, "epoch": 2.834973319625985, "percentage": 94.49, "elapsed_time": "22:59:57", "remaining_time": "1:20:26"}
|
| 370 |
+
{"current_steps": 3630, "total_steps": 3831, "loss": 1.1329906463623047, "lr": 1.6899074423705975e-06, "epoch": 2.8428060899789496, "percentage": 94.75, "elapsed_time": "23:03:37", "remaining_time": "1:16:36"}
|
| 371 |
+
{"current_steps": 3640, "total_steps": 3831, "loss": 1.0851118087768554, "lr": 1.5271480633971768e-06, "epoch": 2.8506388603319137, "percentage": 95.01, "elapsed_time": "23:07:18", "remaining_time": "1:12:47"}
|
| 372 |
+
{"current_steps": 3650, "total_steps": 3831, "loss": 1.1162568092346192, "lr": 1.372568258471807e-06, "epoch": 2.858471630684878, "percentage": 95.28, "elapsed_time": "23:11:03", "remaining_time": "1:08:58"}
|
| 373 |
+
{"current_steps": 3660, "total_steps": 3831, "loss": 1.0793692588806152, "lr": 1.2261808676507724e-06, "epoch": 2.866304401037842, "percentage": 95.54, "elapsed_time": "23:14:45", "remaining_time": "1:05:09"}
|
| 374 |
+
{"current_steps": 3670, "total_steps": 3831, "loss": 1.1028385162353516, "lr": 1.0879980504935772e-06, "epoch": 2.874137171390806, "percentage": 95.8, "elapsed_time": "23:18:25", "remaining_time": "1:01:20"}
|
| 375 |
+
{"current_steps": 3680, "total_steps": 3831, "loss": 1.1181939125061036, "lr": 9.580312850529295e-07, "epoch": 2.8819699417437707, "percentage": 96.06, "elapsed_time": "23:22:04", "remaining_time": "0:57:31"}
|
| 376 |
+
{"current_steps": 3690, "total_steps": 3831, "loss": 1.0907830238342284, "lr": 8.362913669213379e-07, "epoch": 2.889802712096735, "percentage": 96.32, "elapsed_time": "23:25:47", "remaining_time": "0:53:43"}
|
| 377 |
+
{"current_steps": 3700, "total_steps": 3831, "loss": 1.080193328857422, "lr": 7.227884083343406e-07, "epoch": 2.897635482449699, "percentage": 96.58, "elapsed_time": "23:29:32", "remaining_time": "0:49:54"}
|
| 378 |
+
{"current_steps": 3710, "total_steps": 3831, "loss": 1.0740805625915528, "lr": 6.175318373306205e-07, "epoch": 2.905468252802663, "percentage": 96.84, "elapsed_time": "23:33:17", "remaining_time": "0:46:05"}
|
| 379 |
+
{"current_steps": 3720, "total_steps": 3831, "loss": 1.1151776313781738, "lr": 5.205303969687658e-07, "epoch": 2.9133010231556273, "percentage": 97.1, "elapsed_time": "23:37:03", "remaining_time": "0:42:16"}
|
| 380 |
+
{"current_steps": 3730, "total_steps": 3831, "loss": 1.1126981735229493, "lr": 4.317921446011286e-07, "epoch": 2.9211337935085915, "percentage": 97.36, "elapsed_time": "23:40:47", "remaining_time": "0:38:28"}
|
| 381 |
+
{"current_steps": 3740, "total_steps": 3831, "loss": 1.1250258445739747, "lr": 3.513244512045155e-07, "epoch": 2.9289665638615556, "percentage": 97.62, "elapsed_time": "23:44:23", "remaining_time": "0:34:39"}
|
| 382 |
+
{"current_steps": 3750, "total_steps": 3831, "loss": 1.0847277641296387, "lr": 2.7913400076787776e-07, "epoch": 2.9367993342145198, "percentage": 97.89, "elapsed_time": "23:47:59", "remaining_time": "0:30:50"}
|
| 383 |
+
{"current_steps": 3760, "total_steps": 3831, "loss": 1.1382882118225097, "lr": 2.1522678973718847e-07, "epoch": 2.9446321045674844, "percentage": 98.15, "elapsed_time": "23:51:43", "remaining_time": "0:27:02"}
|
| 384 |
+
{"current_steps": 3770, "total_steps": 3831, "loss": 1.1251526832580567, "lr": 1.5960812651728552e-07, "epoch": 2.9524648749204485, "percentage": 98.41, "elapsed_time": "23:55:29", "remaining_time": "0:23:13"}
|
| 385 |
+
{"current_steps": 3780, "total_steps": 3831, "loss": 1.097026538848877, "lr": 1.1228263103099101e-07, "epoch": 2.9602976452734127, "percentage": 98.67, "elapsed_time": "23:59:07", "remaining_time": "0:19:24"}
|
| 386 |
+
{"current_steps": 3790, "total_steps": 3831, "loss": 1.0861360549926757, "lr": 7.32542343352849e-08, "epoch": 2.968130415626377, "percentage": 98.93, "elapsed_time": "1 day, 0:02:45", "remaining_time": "0:15:36"}
|
| 387 |
+
{"current_steps": 3800, "total_steps": 3831, "loss": 1.0637449264526366, "lr": 4.2526178294877153e-08, "epoch": 2.975963185979341, "percentage": 99.19, "elapsed_time": "1 day, 0:06:34", "remaining_time": "0:11:48"}
|
| 388 |
+
{"current_steps": 3810, "total_steps": 3831, "loss": 1.1155780792236327, "lr": 2.010101531282338e-08, "epoch": 2.9837959563323055, "percentage": 99.45, "elapsed_time": "1 day, 0:10:16", "remaining_time": "0:07:59"}
|
| 389 |
+
{"current_steps": 3820, "total_steps": 3831, "loss": 1.1184403419494628, "lr": 5.980608118572039e-09, "epoch": 2.9916287266852697, "percentage": 99.71, "elapsed_time": "1 day, 0:13:56", "remaining_time": "0:04:11"}
|
| 390 |
+
{"current_steps": 3830, "total_steps": 3831, "loss": 1.114205551147461, "lr": 1.661296132327017e-10, "epoch": 2.999461497038234, "percentage": 99.97, "elapsed_time": "1 day, 0:17:41", "remaining_time": "0:00:22"}
|
| 391 |
+
{"current_steps": 3831, "total_steps": 3831, "eval_loss": 1.2653985023498535, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1 day, 0:23:20", "remaining_time": "0:00:00"}
|
| 392 |
+
{"current_steps": 3831, "total_steps": 3831, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1 day, 0:23:26", "remaining_time": "0:00:00"}
|