Text Generation
Transformers
Safetensors
friday
vision-language
multimodal
custom_code
bf16
conversational
Instructions to use kevin510/friday with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kevin510/friday with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kevin510/friday", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("kevin510/friday", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use kevin510/friday with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kevin510/friday" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kevin510/friday", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/kevin510/friday
- SGLang
How to use kevin510/friday 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 "kevin510/friday" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kevin510/friday", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "kevin510/friday" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kevin510/friday", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use kevin510/friday with Docker Model Runner:
docker model run hf.co/kevin510/friday
Update config.json
Browse files- config.json +0 -8
config.json
CHANGED
|
@@ -6,19 +6,13 @@
|
|
| 6 |
},
|
| 7 |
"_cfg_vision_adapter": {
|
| 8 |
"activation": "gelu",
|
| 9 |
-
"checkpoint_path": "./model/mm_projector.bin",
|
| 10 |
-
"device": "cpu",
|
| 11 |
-
"freeze": false,
|
| 12 |
"hidden_dim": 3072,
|
| 13 |
"input_dim": 6144,
|
| 14 |
-
"layers": 2,
|
| 15 |
"num_layers": 2,
|
| 16 |
"output_dim": 3072
|
| 17 |
},
|
| 18 |
"_cfg_vision_tower": {
|
| 19 |
-
"freeze": false,
|
| 20 |
"model_params": {
|
| 21 |
-
"device_map": "cpu",
|
| 22 |
"trust_remote_code": true
|
| 23 |
},
|
| 24 |
"pad_to_square": true,
|
|
@@ -35,10 +29,8 @@
|
|
| 35 |
"auto_map": {
|
| 36 |
"AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
|
| 37 |
"AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
|
| 38 |
-
"AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
|
| 39 |
},
|
| 40 |
"bos_token_id": 199999,
|
| 41 |
-
"delay_load": true,
|
| 42 |
"embd_pdrop": 0.0,
|
| 43 |
"eos_token_id": 199999,
|
| 44 |
"full_attn_mod": 1,
|
|
|
|
| 6 |
},
|
| 7 |
"_cfg_vision_adapter": {
|
| 8 |
"activation": "gelu",
|
|
|
|
|
|
|
|
|
|
| 9 |
"hidden_dim": 3072,
|
| 10 |
"input_dim": 6144,
|
|
|
|
| 11 |
"num_layers": 2,
|
| 12 |
"output_dim": 3072
|
| 13 |
},
|
| 14 |
"_cfg_vision_tower": {
|
|
|
|
| 15 |
"model_params": {
|
|
|
|
| 16 |
"trust_remote_code": true
|
| 17 |
},
|
| 18 |
"pad_to_square": true,
|
|
|
|
| 29 |
"auto_map": {
|
| 30 |
"AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
|
| 31 |
"AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
|
|
|
|
| 32 |
},
|
| 33 |
"bos_token_id": 199999,
|
|
|
|
| 34 |
"embd_pdrop": 0.0,
|
| 35 |
"eos_token_id": 199999,
|
| 36 |
"full_attn_mod": 1,
|