Instructions to use llmware/slim-emotions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmware/slim-emotions with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="llmware/slim-emotions")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("llmware/slim-emotions") model = AutoModelForCausalLM.from_pretrained("llmware/slim-emotions") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use llmware/slim-emotions with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llmware/slim-emotions" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llmware/slim-emotions", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/llmware/slim-emotions
- SGLang
How to use llmware/slim-emotions 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 "llmware/slim-emotions" \ --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": "llmware/slim-emotions", "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 "llmware/slim-emotions" \ --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": "llmware/slim-emotions", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use llmware/slim-emotions with Docker Model Runner:
docker model run hf.co/llmware/slim-emotions
Update config.json
Browse files- config.json +0 -15
config.json
CHANGED
|
@@ -1,10 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"aib_version": "model_archive_122723_tiny_llama-1.1b-29",
|
| 3 |
-
"training_dataset": [
|
| 4 |
-
"aib_label_samples_524s.jsonl"
|
| 5 |
-
],
|
| 6 |
-
"training_timestamp": "Wed Dec 27 17:43:21 2023",
|
| 7 |
-
"training_comments": "tiny-llama-1.1b-27",
|
| 8 |
"vocab_size": 32000,
|
| 9 |
"max_position_embeddings": 2048,
|
| 10 |
"hidden_size": 2048,
|
|
@@ -64,15 +58,6 @@
|
|
| 64 |
"architectures": [
|
| 65 |
"LlamaForCausalLM"
|
| 66 |
],
|
| 67 |
-
"finetuning_task": null,
|
| 68 |
-
"id2label": {
|
| 69 |
-
"0": "LABEL_0",
|
| 70 |
-
"1": "LABEL_1"
|
| 71 |
-
},
|
| 72 |
-
"label2id": {
|
| 73 |
-
"LABEL_0": 0,
|
| 74 |
-
"LABEL_1": 1
|
| 75 |
-
},
|
| 76 |
"tokenizer_class": null,
|
| 77 |
"prefix": null,
|
| 78 |
"bos_token_id": 1,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"vocab_size": 32000,
|
| 3 |
"max_position_embeddings": 2048,
|
| 4 |
"hidden_size": 2048,
|
|
|
|
| 58 |
"architectures": [
|
| 59 |
"LlamaForCausalLM"
|
| 60 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
"tokenizer_class": null,
|
| 62 |
"prefix": null,
|
| 63 |
"bos_token_id": 1,
|