Text Generation
Transformers
English
mistral
Merge
mergekit
lazymergekit
google/gemma-7b
SuperAGI/SAM
Instructions to use Or4cl3-1/Agent_Gemma_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Or4cl3-1/Agent_Gemma_7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Or4cl3-1/Agent_Gemma_7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Or4cl3-1/Agent_Gemma_7b") model = AutoModelForCausalLM.from_pretrained("Or4cl3-1/Agent_Gemma_7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Or4cl3-1/Agent_Gemma_7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Or4cl3-1/Agent_Gemma_7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Or4cl3-1/Agent_Gemma_7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Or4cl3-1/Agent_Gemma_7b
- SGLang
How to use Or4cl3-1/Agent_Gemma_7b 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 "Or4cl3-1/Agent_Gemma_7b" \ --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": "Or4cl3-1/Agent_Gemma_7b", "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 "Or4cl3-1/Agent_Gemma_7b" \ --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": "Or4cl3-1/Agent_Gemma_7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Or4cl3-1/Agent_Gemma_7b with Docker Model Runner:
docker model run hf.co/Or4cl3-1/Agent_Gemma_7b
Update config.json
Browse files- config.json +30 -3
config.json
CHANGED
|
@@ -19,8 +19,35 @@
|
|
| 19 |
"rope_theta": 10000.0,
|
| 20 |
"sliding_window": 4096,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
-
"torch_dtype": "
|
| 23 |
"transformers_version": "4.36.2",
|
| 24 |
"use_cache": true,
|
| 25 |
-
"
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"rope_theta": 10000.0,
|
| 20 |
"sliding_window": 4096,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
"transformers_version": "4.36.2",
|
| 24 |
"use_cache": true,
|
| 25 |
+
"sources": [
|
| 26 |
+
{
|
| 27 |
+
"model": "google/gemma-7b",
|
| 28 |
+
"layer_range": [0, 32]
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"model": "SuperAGI/SAM",
|
| 32 |
+
"layer_range": [0, 32]
|
| 33 |
+
}
|
| 34 |
+
],
|
| 35 |
+
"merge_method": "slerp",
|
| 36 |
+
"base_model": "google/gemma-7b",
|
| 37 |
+
"parameters": {
|
| 38 |
+
"t": [
|
| 39 |
+
{
|
| 40 |
+
"filter": "self_attn",
|
| 41 |
+
"value": [0, 0.5, 0.3, 0.7, 1]
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"filter": "mlp",
|
| 45 |
+
"value": [1, 0.5, 0.7, 0.3, 0]
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"value": 0.5
|
| 49 |
+
}
|
| 50 |
+
]
|
| 51 |
+
},
|
| 52 |
+
"dtype": "bfloat16"
|
| 53 |
+
}
|