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

Libraries

How to use TheNateTCY/testing_opt_actual_model with Transformers:

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

pipe = pipeline("text-generation", model="TheNateTCY/testing_opt_actual_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheNateTCY/testing_opt_actual_model")
model = AutoModelForCausalLM.from_pretrained("TheNateTCY/testing_opt_actual_model")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheNateTCY/testing_opt_actual_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheNateTCY/testing_opt_actual_model

SGLang

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

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

TheNateTCY commited on Dec 21, 2022

Commit

c2fc631

1 Parent(s): ca59b0c

Training in progress epoch 0

Browse files

Files changed (4) hide show

README.md +4 -4
config.json +1 -1
tf_model.h5 +1 -1
tokenizer_config.json +1 -1

README.md CHANGED Viewed

@@ -12,10 +12,10 @@ probably proofread and complete it, then remove this comment. -->
 # TheNateTCY/testing_opt_actual_model
-This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.6162
-- Validation Loss: 2.0981
 - Epoch: 0
 ## Model description
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.6162     | 2.0981          | 0     |
 ### Framework versions

 # TheNateTCY/testing_opt_actual_model
+This model is a fine-tuned version of [TheNateTCY/testing_opt_actual_model](https://huggingface.co/TheNateTCY/testing_opt_actual_model) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 2.0580
+- Validation Loss: 1.6810
 - Epoch: 0
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
+| 2.0580     | 1.6810          | 0     |
 ### Framework versions

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-125m",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",

 {
+  "_name_or_path": "TheNateTCY/testing_opt_actual_model",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60c2896b678d9171aa485d5845765f0f2907190b68117c2d30051515b7b01c0
 size 501169176

 version https://git-lfs.github.com/spec/v1
+oid sha256:5da296dfa08141b5515456a04d58bfad09e5332ae0fee376af2dbae12a982a3d
 size 501169176

tokenizer_config.json CHANGED Viewed

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 1024,
-  "name_or_path": "gpt2",
   "pad_token": null,
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",

   },
   "errors": "replace",
   "model_max_length": 1024,
+  "name_or_path": "TheNateTCY/testing_opt_actual_model",
   "pad_token": null,
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",