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

Libraries

How to use Ksjsjjdj/hghj with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-270m")
model = PeftModel.from_pretrained(base_model, "Ksjsjjdj/hghj")

Transformers

How to use Ksjsjjdj/hghj with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ksjsjjdj/hghj")
model = AutoModelForCausalLM.from_pretrained("Ksjsjjdj/hghj")
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 Ksjsjjdj/hghj with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ksjsjjdj/hghj

SGLang

How to use Ksjsjjdj/hghj 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 "Ksjsjjdj/hghj" \
    --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": "Ksjsjjdj/hghj",
		"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 "Ksjsjjdj/hghj" \
        --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": "Ksjsjjdj/hghj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Ksjsjjdj commited on Nov 30, 2025

Commit

a4d81aa

verified ·

1 Parent(s): 0922efa

Live Checkpoint 3

Browse files

Files changed (6) hide show

adapter_config.json +2 -2
adapter_model.safetensors +2 -2
optimizer.pt +2 -2
rng_state.pth +2 -2
trainer_state.json +6 -6
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 104,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -25,7 +25,7 @@
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
-  "r": 200,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 512,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e3e3e6d69ab8bf663f5fa64ef76c4c16b91d3ad46935cab911fff52f21e330
-size 73747392

 version https://git-lfs.github.com/spec/v1
+oid sha256:36c7253b4ba70ab65aa934ce811f7be3a0cf368aad73b4ac1bff12f95e9577da
+size 94391240

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e239d4c6af1c8fc4e6fce227710b73843ee6c02f69be2b6dd1ce43f619f08d8c
-size 147573899

 version https://git-lfs.github.com/spec/v1
+oid sha256:fcbf02964e210661f85c4d37097b6f9327a6c0dd2b34d11224ee8d7d1d0b7850
+size 188862155

rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1feb2393d444411081aa60ebdb29ea2c48b3bc2ccfc9ce86899de522cb26ec
-size 14455

 version https://git-lfs.github.com/spec/v1
+oid sha256:e9e13dd4ca4af08228a91634a046f6bdd24626ae522be4fbdf8f03b3a08819fb
+size 14391

trainer_state.json CHANGED Viewed

@@ -11,23 +11,23 @@
   "log_history": [
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 1.8294399976730347,
       "learning_rate": 0.0002,
       "loss": 2.2678,
       "step": 1
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 1.3883302211761475,
       "learning_rate": 0.00013333333333333334,
-      "loss": 1.8692,
       "step": 2
     },
     {
       "epoch": 1.0,
-      "grad_norm": 1.213472843170166,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 1.8266,
       "step": 3
     }
   ],
@@ -48,7 +48,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1813434904320.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

   "log_history": [
     {
       "epoch": 0.3333333333333333,
+      "grad_norm": 8.043458938598633,
       "learning_rate": 0.0002,
       "loss": 2.2678,
       "step": 1
     },
     {
       "epoch": 0.6666666666666666,
+      "grad_norm": 26.383363723754883,
       "learning_rate": 0.00013333333333333334,
+      "loss": 2.4716,
       "step": 2
     },
     {
       "epoch": 1.0,
+      "grad_norm": 9.134888648986816,
       "learning_rate": 6.666666666666667e-05,
+      "loss": 2.1976,
       "step": 3
     }
   ],
       "attributes": {}
     }
   },
+  "total_flos": 1892242763520.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3078edd2666b04ce93c65237cae2b17a52d1969fdcd17bf5fde40b98b6a346f
 size 5905

 version https://git-lfs.github.com/spec/v1
+oid sha256:92ad46923c8c77887df1899b19b2cff8af20805ac59096ce09e3dac9d8652b47
 size 5905