Instructions to use kaytoo2022/codet5_react_typescript with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kaytoo2022/codet5_react_typescript with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kaytoo2022/codet5_react_typescript")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("kaytoo2022/codet5_react_typescript") model = AutoModelForSeq2SeqLM.from_pretrained("kaytoo2022/codet5_react_typescript", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kaytoo2022/codet5_react_typescript with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kaytoo2022/codet5_react_typescript" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kaytoo2022/codet5_react_typescript", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kaytoo2022/codet5_react_typescript
- SGLang
How to use kaytoo2022/codet5_react_typescript 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 "kaytoo2022/codet5_react_typescript" \ --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": "kaytoo2022/codet5_react_typescript", "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 "kaytoo2022/codet5_react_typescript" \ --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": "kaytoo2022/codet5_react_typescript", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kaytoo2022/codet5_react_typescript with Docker Model Runner:
docker model run hf.co/kaytoo2022/codet5_react_typescript
Commit ·
60110ad
1
Parent(s): 55df853
Training in progress epoch 0
Browse files- README.md +4 -12
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -6,10 +6,6 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: kaytoo2022/codet5_react_typescript
|
| 8 |
results: []
|
| 9 |
-
inference: true
|
| 10 |
-
library_name: transformers
|
| 11 |
-
pipeline_tag: text2text-generation
|
| 12 |
-
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
@@ -19,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Train Loss:
|
| 23 |
-
- Validation Loss: 0.
|
| 24 |
-
- Epoch:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -47,11 +43,7 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
| Train Loss | Validation Loss | Epoch |
|
| 49 |
|:----------:|:---------------:|:-----:|
|
| 50 |
-
| 1.
|
| 51 |
-
| 0.8779 | 0.8694 | 1 |
|
| 52 |
-
| 0.7559 | 0.8311 | 2 |
|
| 53 |
-
| 0.6684 | 0.8065 | 3 |
|
| 54 |
-
| 0.5915 | 0.7883 | 4 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: kaytoo2022/codet5_react_typescript
|
| 8 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 1.1363
|
| 19 |
+
- Validation Loss: 0.9843
|
| 20 |
+
- Epoch: 0
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 43 |
|
| 44 |
| Train Loss | Validation Loss | Epoch |
|
| 45 |
|:----------:|:---------------:|:-----:|
|
| 46 |
+
| 1.1363 | 0.9843 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089286000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af7e56ab937ad76da9893b25cddcf37e591a062b21c80dbd43aa3c7d9a097c9f
|
| 3 |
size 1089286000
|