Instructions to use GerbilLab/GerbilCode-77m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GerbilLab/GerbilCode-77m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GerbilLab/GerbilCode-77m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GerbilLab/GerbilCode-77m") model = AutoModelForCausalLM.from_pretrained("GerbilLab/GerbilCode-77m") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use GerbilLab/GerbilCode-77m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GerbilLab/GerbilCode-77m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GerbilLab/GerbilCode-77m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GerbilLab/GerbilCode-77m
- SGLang
How to use GerbilLab/GerbilCode-77m 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 "GerbilLab/GerbilCode-77m" \ --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": "GerbilLab/GerbilCode-77m", "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 "GerbilLab/GerbilCode-77m" \ --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": "GerbilLab/GerbilCode-77m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GerbilLab/GerbilCode-77m with Docker Model Runner:
docker model run hf.co/GerbilLab/GerbilCode-77m
Upload GPTJForCausalLM
Browse files- config.json +26 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "GerbilLab/GerbilBlender-B-star-77m",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTJForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gptj",
|
| 14 |
+
"n_embd": 512,
|
| 15 |
+
"n_head": 8,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 8,
|
| 18 |
+
"n_positions": 2048,
|
| 19 |
+
"resid_pdrop": 0.0,
|
| 20 |
+
"rotary_dim": 64,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.29.0.dev0",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 50264
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.29.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:166d23ad52960774f7c409bd9c3c224963b37150862c5960becdd7b76f38be9b
|
| 3 |
+
size 187019425
|