Instructions to use ninagroot/Llama-360M-finaltest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ninagroot/Llama-360M-finaltest with Transformers:

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

pipe = pipeline("text-generation", model="ninagroot/Llama-360M-finaltest")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ninagroot/Llama-360M-finaltest")
model = AutoModelForCausalLM.from_pretrained("ninagroot/Llama-360M-finaltest", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ninagroot/Llama-360M-finaltest with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ninagroot/Llama-360M-finaltest"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ninagroot/Llama-360M-finaltest",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ninagroot/Llama-360M-finaltest

SGLang

How to use ninagroot/Llama-360M-finaltest 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 "ninagroot/Llama-360M-finaltest" \
    --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": "ninagroot/Llama-360M-finaltest",
		"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 "ninagroot/Llama-360M-finaltest" \
        --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": "ninagroot/Llama-360M-finaltest",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ninagroot/Llama-360M-finaltest with Docker Model Runner:
```
docker model run hf.co/ninagroot/Llama-360M-finaltest
```

ninagroot commited on May 31, 2024

Commit

5f19a49

verified ·

1 Parent(s): 52c02fc

ninagroot/Llama-360M

Browse files

Files changed (5) hide show

README.md +21 -21
model.safetensors +1 -1
runs/May31_11-32-10_gcn9.local.snellius.surf.nl/events.out.tfevents.1717147938.gcn9.local.snellius.surf.nl.3055809.0 +3 -0
runs/May31_11-40-07_gcn15.local.snellius.surf.nl/events.out.tfevents.1717148416.gcn15.local.snellius.surf.nl.1595217.0 +3 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8573
 ## Model description
@@ -48,26 +48,26 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 8.5748        | 1.0   | 3    | 8.5145          |
-| 8.2938        | 2.0   | 6    | 8.2723          |
-| 7.8473        | 3.0   | 9    | 7.8807          |
-| 7.2394        | 4.0   | 12   | 7.3951          |
-| 6.6519        | 5.0   | 15   | 6.9171          |
-| 6.2694        | 6.0   | 18   | 6.5824          |
-| 5.9992        | 7.0   | 21   | 6.3622          |
-| 5.9116        | 8.0   | 24   | 6.1503          |
-| 5.6323        | 9.0   | 27   | 5.8219          |
-| 5.1124        | 10.0  | 30   | 5.4438          |
-| 4.6146        | 11.0  | 33   | 5.1114          |
-| 4.4062        | 12.0  | 36   | 4.8742          |
-| 3.967         | 13.0  | 39   | 4.6720          |
-| 3.9281        | 14.0  | 42   | 4.4782          |
-| 3.5204        | 15.0  | 45   | 4.2976          |
-| 3.3159        | 16.0  | 48   | 4.1650          |
-| 3.1737        | 17.0  | 51   | 4.0546          |
-| 2.9307        | 18.0  | 54   | 3.9636          |
-| 2.8228        | 19.0  | 57   | 3.9233          |
-| 2.8805        | 20.0  | 60   | 3.8573          |
 ### Framework versions

 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 3.8245
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 8.6417        | 1.0   | 3    | 8.5751          |
+| 8.3908        | 2.0   | 6    | 8.3473          |
+| 7.9583        | 3.0   | 9    | 7.9814          |
+| 7.3598        | 4.0   | 12   | 7.5011          |
+| 6.7468        | 5.0   | 15   | 6.9942          |
+| 6.3345        | 6.0   | 18   | 6.6309          |
+| 6.0489        | 7.0   | 21   | 6.3987          |
+| 5.9651        | 8.0   | 24   | 6.2101          |
+| 5.7683        | 9.0   | 27   | 5.9691          |
+| 5.3051        | 10.0  | 30   | 5.5791          |
+| 4.6791        | 11.0  | 33   | 5.1445          |
+| 4.3962        | 12.0  | 36   | 4.8859          |
+| 4.0007        | 13.0  | 39   | 4.7013          |
+| 3.9473        | 14.0  | 42   | 4.4994          |
+| 3.5486        | 15.0  | 45   | 4.3178          |
+| 3.3243        | 16.0  | 48   | 4.1587          |
+| 3.1305        | 17.0  | 51   | 4.0505          |
+| 2.8703        | 18.0  | 54   | 3.9467          |
+| 2.7661        | 19.0  | 57   | 3.8780          |
+| 2.7976        | 20.0  | 60   | 3.8245          |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3191db7e07bae151278dfdabc1a220f74f843ac6b35d12e8a39986976b7810f5
 size 1344794872

 version https://git-lfs.github.com/spec/v1
+oid sha256:684b8806d391ce3045007074aaf6d1634f0ef3abfd1ee3a2d67920326b92d963
 size 1344794872

runs/May31_11-32-10_gcn9.local.snellius.surf.nl/events.out.tfevents.1717147938.gcn9.local.snellius.surf.nl.3055809.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:82d968e00f2ffdbb5f406e847656110a23eba19560619846cf9e6d53b5f86dc3
+size 22649

runs/May31_11-40-07_gcn15.local.snellius.surf.nl/events.out.tfevents.1717148416.gcn15.local.snellius.surf.nl.1595217.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7b82e0ef5af50e96acbce62a91884344a4bf96b722347e37172d5aa7e8c299
+size 22650

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a42bb0d2a69c86d81febc61f8377e6208a44e801166f3260acf591518ad0e5
 size 4984

 version https://git-lfs.github.com/spec/v1
+oid sha256:e308ebcbb613aa25beff2bdb51a8006624705074536254a3fe29a768a1ccbdcb
 size 4984