Instructions to use legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k with Transformers:

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

pipe = pipeline("text-generation", model="legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k

SGLang

How to use legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k 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 "legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k 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 legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k 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 legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k",
    max_seq_length=2048,
)

Docker Model Runner
How to use legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k with Docker Model Runner:
```
docker model run hf.co/legesher/language-decoded-lora-phase-2-the-stack-v1-condition-3-zh-5k
```

Rashik24 commited on Mar 23

Commit

759f176

verified ·

1 Parent(s): 9928483

Upload training_metrics.json

Browse files

Files changed (1) hide show

training_metrics.json +207 -0

training_metrics.json ADDED Viewed

	@@ -0,0 +1,207 @@

+[
+  {
+    "loss": 1.3593,
+    "grad_norm": 0.07132186740636826,
+    "learning_rate": 0.00012,
+    "epoch": 0.03546099290780142,
+    "step": 10
+  },
+  {
+    "loss": 1.2212,
+    "grad_norm": 0.06576087325811386,
+    "learning_rate": 0.00019988926445681492,
+    "epoch": 0.07092198581560284,
+    "step": 20
+  },
+  {
+    "loss": 1.4382,
+    "grad_norm": 0.064721018075943,
+    "learning_rate": 0.0001986463043917528,
+    "epoch": 0.10638297872340426,
+    "step": 30
+  },
+  {
+    "loss": 1.1636,
+    "grad_norm": 0.06784526258707047,
+    "learning_rate": 0.00019603921063437793,
+    "epoch": 0.14184397163120568,
+    "step": 40
+  },
+  {
+    "loss": 1.1023,
+    "grad_norm": 0.06855457276105881,
+    "learning_rate": 0.0001921040354671897,
+    "epoch": 0.1773049645390071,
+    "step": 50
+  },
+  {
+    "loss": 1.159,
+    "grad_norm": 0.0872117206454277,
+    "learning_rate": 0.00018689519659051467,
+    "epoch": 0.2127659574468085,
+    "step": 60
+  },
+  {
+    "loss": 1.2097,
+    "grad_norm": 0.06708938628435135,
+    "learning_rate": 0.00018048472460553257,
+    "epoch": 0.24822695035460993,
+    "step": 70
+  },
+  {
+    "loss": 1.1172,
+    "grad_norm": 0.07587900757789612,
+    "learning_rate": 0.00017296126693671884,
+    "epoch": 0.28368794326241137,
+    "step": 80
+  },
+  {
+    "loss": 1.0976,
+    "grad_norm": 0.07327847182750702,
+    "learning_rate": 0.00016442886196799464,
+    "epoch": 0.3191489361702128,
+    "step": 90
+  },
+  {
+    "loss": 1.1342,
+    "grad_norm": 0.07166396826505661,
+    "learning_rate": 0.00015500550034448413,
+    "epoch": 0.3546099290780142,
+    "step": 100
+  },
+  {
+    "loss": 1.1876,
+    "grad_norm": 0.08132865279912949,
+    "learning_rate": 0.00014482149333496454,
+    "epoch": 0.3900709219858156,
+    "step": 110
+  },
+  {
+    "loss": 1.2186,
+    "grad_norm": 0.08324161171913147,
+    "learning_rate": 0.0001340176708181637,
+    "epoch": 0.425531914893617,
+    "step": 120
+  },
+  {
+    "loss": 1.2672,
+    "grad_norm": 0.08210298418998718,
+    "learning_rate": 0.00012274343381211066,
+    "epoch": 0.46099290780141844,
+    "step": 130
+  },
+  {
+    "loss": 1.1838,
+    "grad_norm": 0.06662478297948837,
+    "learning_rate": 0.00011115468847720245,
+    "epoch": 0.49645390070921985,
+    "step": 140
+  },
+  {
+    "loss": 1.161,
+    "grad_norm": 0.08010110259056091,
+    "learning_rate": 9.941169016269379e-05,
+    "epoch": 0.5319148936170213,
+    "step": 150
+  },
+  {
+    "loss": 1.2318,
+    "grad_norm": 0.09503161162137985,
+    "learning_rate": 8.767682731028415e-05,
+    "epoch": 0.5673758865248227,
+    "step": 160
+  },
+  {
+    "loss": 1.1064,
+    "grad_norm": 0.06613818556070328,
+    "learning_rate": 7.611237586016557e-05,
+    "epoch": 0.6028368794326241,
+    "step": 170
+  },
+  {
+    "loss": 1.1023,
+    "grad_norm": 0.08144712448120117,
+    "learning_rate": 6.487825521280109e-05,
+    "epoch": 0.6382978723404256,
+    "step": 180
+  },
+  {
+    "loss": 1.0777,
+    "grad_norm": 0.07447583973407745,
+    "learning_rate": 5.4129816778190936e-05,
+    "epoch": 0.6737588652482269,
+    "step": 190
+  },
+  {
+    "loss": 1.0299,
+    "grad_norm": 0.08357255160808563,
+    "learning_rate": 4.401569569374668e-05,
+    "epoch": 0.7092198581560284,
+    "step": 200
+  },
+  {
+    "loss": 1.1504,
+    "grad_norm": 0.07654684036970139,
+    "learning_rate": 3.467575541836305e-05,
+    "epoch": 0.7446808510638298,
+    "step": 210
+  },
+  {
+    "loss": 1.0784,
+    "grad_norm": 0.07995031774044037,
+    "learning_rate": 2.6239153625937784e-05,
+    "epoch": 0.7801418439716312,
+    "step": 220
+  },
+  {
+    "loss": 1.0866,
+    "grad_norm": 0.08516442775726318,
+    "learning_rate": 1.882255614419376e-05,
+    "epoch": 0.8156028368794326,
+    "step": 230
+  },
+  {
+    "loss": 1.1881,
+    "grad_norm": 0.06854885816574097,
+    "learning_rate": 1.2528523637410838e-05,
+    "epoch": 0.851063829787234,
+    "step": 240
+  },
+  {
+    "loss": 1.1803,
+    "grad_norm": 0.07308827340602875,
+    "learning_rate": 7.4440933428779e-06,
+    "epoch": 0.8865248226950354,
+    "step": 250
+  },
+  {
+    "loss": 1.252,
+    "grad_norm": 0.082114577293396,
+    "learning_rate": 3.6395754735699894e-06,
+    "epoch": 0.9219858156028369,
+    "step": 260
+  },
+  {
+    "loss": 0.9981,
+    "grad_norm": 0.08104278147220612,
+    "learning_rate": 1.1675809310361497e-06,
+    "epoch": 0.9574468085106383,
+    "step": 270
+  },
+  {
+    "loss": 1.0975,
+    "grad_norm": 0.1148340180516243,
+    "learning_rate": 6.229377380218005e-08,
+    "epoch": 0.9929078014184397,
+    "step": 280
+  },
+  {
+    "train_runtime": 5043.2773,
+    "train_samples_per_second": 0.892,
+    "train_steps_per_second": 0.056,
+    "total_flos": 7.853598969744589e+16,
+    "train_loss": 1.1630526971309743,
+    "epoch": 1.0,
+    "step": 282
+  }
+]