Instructions to use MosRat/Gex_V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MosRat/Gex_V1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MosRat/Gex_V1", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("MosRat/Gex_V1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MosRat/Gex_V1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MosRat/Gex_V1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MosRat/Gex_V1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/MosRat/Gex_V1
- SGLang
How to use MosRat/Gex_V1 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 "MosRat/Gex_V1" \ --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": "MosRat/Gex_V1", "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 "MosRat/Gex_V1" \ --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": "MosRat/Gex_V1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use MosRat/Gex_V1 with Docker Model Runner:
docker model run hf.co/MosRat/Gex_V1
Upload GexQwenForCausalLM
Browse files- config.json +33 -0
- configuration_gex.py +4 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GexQwenForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_gex.GexConfig",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_gex.GexQwenForCausalLM"
|
| 9 |
+
},
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"eos_token_id": 151643,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 2816,
|
| 16 |
+
"max_position_embeddings": 32768,
|
| 17 |
+
"max_window_layers": 8,
|
| 18 |
+
"model_type": "gex",
|
| 19 |
+
"num_attention_heads": 8,
|
| 20 |
+
"num_hidden_layers": 8,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": null,
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.50.1",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_mrope": false,
|
| 31 |
+
"use_sliding_window": false,
|
| 32 |
+
"vocab_size": 151936
|
| 33 |
+
}
|
configuration_gex.py
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import Qwen2Config
|
| 2 |
+
|
| 3 |
+
class GexConfig(Qwen2Config):
|
| 4 |
+
model_type = "gex"
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.50.1"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:896799e932d917484780c2776cfb8363d51e95b2af58df9c631b3b41bcf41dde
|
| 3 |
+
size 714447688
|