Instructions to use tristayqc/my_awesome_eli5_clm-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tristayqc/my_awesome_eli5_clm-model with Transformers:

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

pipe = pipeline("text-generation", model="tristayqc/my_awesome_eli5_clm-model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tristayqc/my_awesome_eli5_clm-model")
model = AutoModelForCausalLM.from_pretrained("tristayqc/my_awesome_eli5_clm-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tristayqc/my_awesome_eli5_clm-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tristayqc/my_awesome_eli5_clm-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tristayqc/my_awesome_eli5_clm-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tristayqc/my_awesome_eli5_clm-model

SGLang

How to use tristayqc/my_awesome_eli5_clm-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 "tristayqc/my_awesome_eli5_clm-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": "tristayqc/my_awesome_eli5_clm-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 "tristayqc/my_awesome_eli5_clm-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": "tristayqc/my_awesome_eli5_clm-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tristayqc/my_awesome_eli5_clm-model with Docker Model Runner:
```
docker model run hf.co/tristayqc/my_awesome_eli5_clm-model
```

tristayqc commited on Apr 25, 2024

Commit

5f51146

verified ·

1 Parent(s): d90ab69

End of training

Browse files

Files changed (4) hide show

README.md +6 -6
generation_config.json +2 -8
runs/Apr25_02-36-08_bf3541846459/events.out.tfevents.1714012569.bf3541846459.310.0 +2 -2
runs/Apr25_02-36-08_bf3541846459/events.out.tfevents.1714014837.bf3541846459.310.1 +3 -0

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: facebook/bart-base
 tags:
 - generated_from_trainer
 datasets:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # my_awesome_eli5_clm-model
-This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the eli5_category dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0396
 ## Model description
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0493        | 1.0   | 3026 | 0.0398          |
-| 0.0415        | 2.0   | 6052 | 0.0397          |
-| 0.0402        | 3.0   | 9078 | 0.0396          |
 ### Framework versions

 ---
 license: apache-2.0
+base_model: google/bigbird-roberta-base
 tags:
 - generated_from_trainer
 datasets:
 # my_awesome_eli5_clm-model
+This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on the eli5_category dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0044
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 0.0332        | 1.0   | 2000 | 0.0077          |
+| 0.0105        | 2.0   | 4000 | 0.0022          |
+| 0.0091        | 3.0   | 6000 | 0.0044          |
 ### Framework versions

generation_config.json CHANGED Viewed

@@ -1,13 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
   "transformers_version": "4.40.1"
 }

 {
   "_from_model_config": true,
+  "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.40.1"
 }

runs/Apr25_02-36-08_bf3541846459/events.out.tfevents.1714012569.bf3541846459.310.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3acee3a0df1c424c9e9e1eef7bb93dce82dc54006a6c1596d476e92adf3e913b
-size 7986

 version https://git-lfs.github.com/spec/v1
+oid sha256:74486dd1d9f39cf95b3f0f391358260a44d4be645925ed16718d85141c2aee23
+size 8611

runs/Apr25_02-36-08_bf3541846459/events.out.tfevents.1714014837.bf3541846459.310.1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f21a6e7889e0a3734e1bcfc7de2d7e759f124f28793eab457f333d114af44aea
+size 359