Instructions to use nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct")
model = AutoModelForCausalLM.from_pretrained("nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct

SGLang

How to use nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct 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 "nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct" \
    --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": "nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct",
		"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 "nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct" \
        --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": "nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct with Docker Model Runner:
```
docker model run hf.co/nagrajn/TinyLinuxDSLM81M_EXTFULL_Instruct
```

nagrajn commited on Jun 22, 2024

Commit

4105cc6

verified ·

1 Parent(s): 5cc0bd7

End of training

Browse files

Files changed (3) hide show

README.md +5 -4
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [nagrajn/TinyLinuxDSLM81M_EXTFULL](https://huggingface.co/nagrajn/TinyLinuxDSLM81M_EXTFULL) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4482
 ## Model description
@@ -41,14 +41,15 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
 ### Training results
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.4516        | 0.9991 | 843  | 0.4501          |
-| 0.449         | 1.9982 | 1686 | 0.4482          |
 ### Framework versions

 This model is a fine-tuned version of [nagrajn/TinyLinuxDSLM81M_EXTFULL](https://huggingface.co/nagrajn/TinyLinuxDSLM81M_EXTFULL) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5143
 ## Model description
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 3
 ### Training results
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.9194        | 0.9991 | 843  | 0.8285          |
+| 0.7235        | 1.9994 | 1687 | 0.5914          |
+| 0.6104        | 2.9973 | 2529 | 0.5143          |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec786a2bd3c52ea730c8c6585c0102fea8fd3ef136d72d90621b8602a598e516
 size 327670216

 version https://git-lfs.github.com/spec/v1
+oid sha256:6eb12eb0bbfb1a5ebd777ad343adcdb139035afbbb0ac8aa69118317f6fa2a9b
 size 327670216

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d1ba9355366abb060b29568c318dd324253f6dddc9483b7321adfbe76437b1
 size 5176

 version https://git-lfs.github.com/spec/v1
+oid sha256:d22b2a4773fe1cfe94ff90e40751a696f78f5721bde4b51badf6daf47adf3b33
 size 5176