Instructions to use ManiWavelabs/outputs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ManiWavelabs/outputs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ManiWavelabs/outputs", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ManiWavelabs/outputs", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("ManiWavelabs/outputs", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ManiWavelabs/outputs with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ManiWavelabs/outputs" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ManiWavelabs/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ManiWavelabs/outputs
- SGLang
How to use ManiWavelabs/outputs 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 "ManiWavelabs/outputs" \ --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": "ManiWavelabs/outputs", "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 "ManiWavelabs/outputs" \ --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": "ManiWavelabs/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ManiWavelabs/outputs with Docker Model Runner:
docker model run hf.co/ManiWavelabs/outputs
Training in progress, epoch 0
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -16,14 +16,14 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"k_proj",
|
| 20 |
-
"down_proj",
|
| 21 |
"up_proj",
|
| 22 |
"v_proj",
|
|
|
|
|
|
|
| 23 |
"q_proj",
|
| 24 |
"o_proj",
|
| 25 |
"gate_proj",
|
| 26 |
-
"
|
| 27 |
],
|
| 28 |
"task_type": "CASUAL_LM"
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ManiWavelabs/phi2_base_finetune",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
|
|
|
| 19 |
"up_proj",
|
| 20 |
"v_proj",
|
| 21 |
+
"lm_head",
|
| 22 |
+
"down_proj",
|
| 23 |
"q_proj",
|
| 24 |
"o_proj",
|
| 25 |
"gate_proj",
|
| 26 |
+
"k_proj"
|
| 27 |
],
|
| 28 |
"task_type": "CASUAL_LM"
|
| 29 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 279209944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab8cb0a80ef5da7dd3faa82e0c04e24608b65bd232f9f8a4e16a85029239c837
|
| 3 |
size 279209944
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b02c945a56c2d617e67bcee0000bb1b3506511f58cb207c1bf740183e081a089
|
| 3 |
size 4856
|