Instructions to use legesher/language-decoded-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use legesher/language-decoded-lora with Transformers:

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

pipe = pipeline("text-generation", model="legesher/language-decoded-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("legesher/language-decoded-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use legesher/language-decoded-lora 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"
# 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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/legesher/language-decoded-lora

SGLang

How to use legesher/language-decoded-lora 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" \
    --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",
		"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" \
        --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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use legesher/language-decoded-lora 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 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 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 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",
    max_seq_length=2048,
)

Docker Model Runner
How to use legesher/language-decoded-lora with Docker Model Runner:
```
docker model run hf.co/legesher/language-decoded-lora
```

Rashik24 commited on May 18

Commit

1c9b9c0

verified ·

1 Parent(s): 4ed4206

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/adapter_config.json +50 -0
tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/adapter_model.safetensors +3 -0
tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/training_metrics.json +200 -0

tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/adapter_config.json ADDED Viewed

	@@ -0,0 +1,50 @@

+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Cohere2ForCausalLM",
+    "parent_library": "transformers.models.cohere2.modeling_cohere2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "CohereLabs/tiny-aya-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5af7c744e202449077afac9e20f62bc17d626be89552984a24c32bbbd9ac5a
+size 120981200

tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/training_metrics.json ADDED Viewed

	@@ -0,0 +1,200 @@

+{
+  "model_config_name": "tiny-aya-base",
+  "condition_name": "condition-5-ur-5k-c4ai-aya-expanse-32b",
+  "seed": 42,
+  "output_name": "condition-5-ur-5k-c4ai-aya-expanse-32b-seed42",
+  "train_result": {
+    "train_runtime": 2804.4689,
+    "train_samples_per_second": 1.458,
+    "train_steps_per_second": 0.091,
+    "total_flos": 7.153599938507571e+16,
+    "train_loss": 1.497109742835164,
+    "epoch": 1.0
+  },
+  "log_history": [
+    {
+      "loss": 2.1474,
+      "grad_norm": 0.19947971403598785,
+      "learning_rate": 0.00013846153846153847,
+      "epoch": 0.0390625,
+      "step": 10
+    },
+    {
+      "loss": 2.0016,
+      "grad_norm": 0.25411975383758545,
+      "learning_rate": 0.0001996992941167792,
+      "epoch": 0.078125,
+      "step": 20
+    },
+    {
+      "loss": 1.7781,
+      "grad_norm": 0.2441367506980896,
+      "learning_rate": 0.00019786819219718443,
+      "epoch": 0.1171875,
+      "step": 30
+    },
+    {
+      "loss": 1.6418,
+      "grad_norm": 0.2709871828556061,
+      "learning_rate": 0.00019440357285533,
+      "epoch": 0.15625,
+      "step": 40
+    },
+    {
+      "loss": 1.5772,
+      "grad_norm": 0.29235324263572693,
+      "learning_rate": 0.00018936326403234125,
+      "epoch": 0.1953125,
+      "step": 50
+    },
+    {
+      "loss": 1.5232,
+      "grad_norm": 0.3283468782901764,
+      "learning_rate": 0.00018283139349323634,
+      "epoch": 0.234375,
+      "step": 60
+    },
+    {
+      "loss": 1.5117,
+      "grad_norm": 0.3553702235221863,
+      "learning_rate": 0.00017491698465089362,
+      "epoch": 0.2734375,
+      "step": 70
+    },
+    {
+      "loss": 1.5393,
+      "grad_norm": 0.3027332127094269,
+      "learning_rate": 0.0001657521368569064,
+      "epoch": 0.3125,
+      "step": 80
+    },
+    {
+      "loss": 1.4895,
+      "grad_norm": 0.3121708631515503,
+      "learning_rate": 0.0001554898205320797,
+      "epoch": 0.3515625,
+      "step": 90
+    },
+    {
+      "loss": 1.4769,
+      "grad_norm": 0.3325497806072235,
+      "learning_rate": 0.00014430132393803352,
+      "epoch": 0.390625,
+      "step": 100
+    },
+    {
+      "loss": 1.4544,
+      "grad_norm": 0.34160560369491577,
+      "learning_rate": 0.00013237339420583212,
+      "epoch": 0.4296875,
+      "step": 110
+    },
+    {
+      "loss": 1.3783,
+      "grad_norm": 0.3413858115673065,
+      "learning_rate": 0.00011990512034071406,
+      "epoch": 0.46875,
+      "step": 120
+    },
+    {
+      "loss": 1.4287,
+      "grad_norm": 0.41221383213996887,
+      "learning_rate": 0.00010710461022867302,
+      "epoch": 0.5078125,
+      "step": 130
+    },
+    {
+      "loss": 1.3989,
+      "grad_norm": 0.30801457166671753,
+      "learning_rate": 9.418551710895243e-05,
+      "epoch": 0.546875,
+      "step": 140
+    },
+    {
+      "loss": 1.3469,
+      "grad_norm": 0.40253663063049316,
+      "learning_rate": 8.13634734890818e-05,
+      "epoch": 0.5859375,
+      "step": 150
+    },
+    {
+      "loss": 1.3711,
+      "grad_norm": 0.3199004828929901,
+      "learning_rate": 6.885249202395754e-05,
+      "epoch": 0.625,
+      "step": 160
+    },
+    {
+      "loss": 1.3963,
+      "grad_norm": 0.3402356207370758,
+      "learning_rate": 5.6861393431874675e-05,
+      "epoch": 0.6640625,
+      "step": 170
+    },
+    {
+      "loss": 1.3701,
+      "grad_norm": 0.3778349757194519,
+      "learning_rate": 4.559032106914173e-05,
+      "epoch": 0.703125,
+      "step": 180
+    },
+    {
+      "loss": 1.3602,
+      "grad_norm": 0.3515849709510803,
+      "learning_rate": 3.522740033849411e-05,
+      "epoch": 0.7421875,
+      "step": 190
+    },
+    {
+      "loss": 1.4115,
+      "grad_norm": 0.37998726963996887,
+      "learning_rate": 2.594559868909956e-05,
+      "epoch": 0.78125,
+      "step": 200
+    },
+    {
+      "loss": 1.3598,
+      "grad_norm": 0.35443946719169617,
+      "learning_rate": 1.7899838617878163e-05,
+      "epoch": 0.8203125,
+      "step": 210
+    },
+    {
+      "loss": 1.3761,
+      "grad_norm": 0.3722814917564392,
+      "learning_rate": 1.1224411859014417e-05,
+      "epoch": 0.859375,
+      "step": 220
+    },
+    {
+      "loss": 1.3844,
+      "grad_norm": 0.38155126571655273,
+      "learning_rate": 6.030737921409169e-06,
+      "epoch": 0.8984375,
+      "step": 230
+    },
+    {
+      "loss": 1.4358,
+      "grad_norm": 0.38531145453453064,
+      "learning_rate": 2.4055043863096428e-06,
+      "epoch": 0.9375,
+      "step": 240
+    },
+    {
+      "loss": 1.3806,
+      "grad_norm": 0.36546796560287476,
+      "learning_rate": 4.092200053990691e-07,
+      "epoch": 0.9765625,
+      "step": 250
+    },
+    {
+      "train_runtime": 2804.4689,
+      "train_samples_per_second": 1.458,
+      "train_steps_per_second": 0.091,
+      "total_flos": 7.153599938507571e+16,
+      "train_loss": 1.497109742835164,
+      "epoch": 1.0,
+      "step": 256
+    }
+  ]
+}