Instructions to use ninagroot/Llama-360M-RUN1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ninagroot/Llama-360M-RUN1 with Transformers:

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

pipe = pipeline("text-generation", model="ninagroot/Llama-360M-RUN1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ninagroot/Llama-360M-RUN1")
model = AutoModelForCausalLM.from_pretrained("ninagroot/Llama-360M-RUN1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ninagroot/Llama-360M-RUN1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ninagroot/Llama-360M-RUN1"
# 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-RUN1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ninagroot/Llama-360M-RUN1

SGLang

How to use ninagroot/Llama-360M-RUN1 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-RUN1" \
    --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-RUN1",
		"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-RUN1" \
        --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-RUN1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ninagroot/Llama-360M-RUN1 with Docker Model Runner:
```
docker model run hf.co/ninagroot/Llama-360M-RUN1
```

ninagroot commited on Mar 20, 2024

Commit

c2b65a9

verified ·

1 Parent(s): 5bfc8f4

ninagroot/Llama-360Mtest

Browse files

Files changed (4) hide show

README.md +20 -6
model.safetensors +1 -1
runs/Mar20_14-33-09_gcn44.local.snellius.surf.nl/events.out.tfevents.1710941597.gcn44.local.snellius.surf.nl.624542.0 +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: 8.2764
 ## Model description
@@ -41,17 +41,31 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 300
-- num_epochs: 4
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.89  | 2    | 8.5545          |
-| No log        | 1.78  | 4    | 8.5018          |
-| No log        | 2.67  | 6    | 8.4091          |
-| No log        | 3.56  | 8    | 8.2764          |
 ### 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: 5.9655
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 300
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.89  | 2    | 8.5679          |
+| No log        | 1.78  | 4    | 8.5182          |
+| No log        | 2.67  | 6    | 8.4304          |
+| No log        | 4.0   | 9    | 8.2278          |
+| No log        | 4.89  | 11   | 8.0473          |
+| No log        | 5.78  | 13   | 7.8459          |
+| No log        | 6.67  | 15   | 7.6372          |
+| No log        | 8.0   | 18   | 7.3787          |
+| 7.9918        | 8.89  | 20   | 7.1956          |
+| 7.9918        | 9.78  | 22   | 7.0644          |
+| 7.9918        | 10.67 | 24   | 6.9150          |
+| 7.9918        | 12.0  | 27   | 6.7280          |
+| 7.9918        | 12.89 | 29   | 6.5960          |
+| 7.9918        | 13.78 | 31   | 6.4792          |
+| 7.9918        | 14.67 | 33   | 6.3487          |
+| 7.9918        | 16.0  | 36   | 6.1616          |
+| 7.9918        | 16.89 | 38   | 6.0606          |
+| 6.3677        | 17.78 | 40   | 5.9655          |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8177d7dce9ccc7fe15c2f39e9889ac0b5a28059453f66da83d3a4ec1f938d295
 size 1344172280

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd7d3b9032857420cb3030328c76375a6bb5f32b36c42f25f16f07a6eccf4255
 size 1344172280

runs/Mar20_14-33-09_gcn44.local.snellius.surf.nl/events.out.tfevents.1710941597.gcn44.local.snellius.surf.nl.624542.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:fef01474436e95c41e6f9a334f4e2e8bfd5beb5031218b65bf7e74bf851b18fe
+size 9764

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1eac06fa6a81dfd6cee717c8e16104728e75f8a169ec4c91b67bba4b5245c90
 size 4728

 version https://git-lfs.github.com/spec/v1
+oid sha256:854943628158b4953c8db55688afec58f9d4beac612540e46ff06bd58dd3e71c
 size 4728