Instructions to use jstet/myrtle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jstet/myrtle with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jstet/myrtle")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jstet/myrtle") model = AutoModelForCausalLM.from_pretrained("jstet/myrtle", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jstet/myrtle with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jstet/myrtle" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jstet/myrtle", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jstet/myrtle
- SGLang
How to use jstet/myrtle 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 "jstet/myrtle" \ --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": "jstet/myrtle", "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 "jstet/myrtle" \ --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": "jstet/myrtle", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jstet/myrtle with Docker Model Runner:
docker model run hf.co/jstet/myrtle
Training in progress, epoch 1
Browse files- config.json +4 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -29,7 +29,10 @@
|
|
| 29 |
"task_specific_params": {
|
| 30 |
"text-generation": {
|
| 31 |
"do_sample": true,
|
| 32 |
-
"max_length":
|
|
|
|
|
|
|
|
|
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"torch_dtype": "float32",
|
|
|
|
| 29 |
"task_specific_params": {
|
| 30 |
"text-generation": {
|
| 31 |
"do_sample": true,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 100,
|
| 34 |
+
"temperature": 1.0,
|
| 35 |
+
"top_p": 0.95
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"torch_dtype": "float32",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497807197
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92689ec39547db118ae6a43b2077899ee54148fcf6b5396544a4f5e7c2e40cd0
|
| 3 |
size 497807197
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13451c477e80caacba2498f9e45c83ac49da731860943bb6a005b993a05e9784
|
| 3 |
size 3963
|