Instructions to use goldfish-models/san_deva_10mb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use goldfish-models/san_deva_10mb with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="goldfish-models/san_deva_10mb")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("goldfish-models/san_deva_10mb")
model = AutoModelForCausalLM.from_pretrained("goldfish-models/san_deva_10mb")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use goldfish-models/san_deva_10mb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "goldfish-models/san_deva_10mb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "goldfish-models/san_deva_10mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/goldfish-models/san_deva_10mb

SGLang

How to use goldfish-models/san_deva_10mb 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 "goldfish-models/san_deva_10mb" \
    --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": "goldfish-models/san_deva_10mb",
		"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 "goldfish-models/san_deva_10mb" \
        --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": "goldfish-models/san_deva_10mb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use goldfish-models/san_deva_10mb with Docker Model Runner:
```
docker model run hf.co/goldfish-models/san_deva_10mb
```

goldfish-models commited on Aug 13, 2024

Commit

22aa42b

1 Parent(s): 9ce4928

Upload san_deva_10mb model.

Browse files

Files changed (2) hide show

config.json +34 -0
pytorch_model.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,34 @@

+{
+  "_name_or_path": "models/10mb/san_deva_10mb",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "n_positions": 512,
+  "pad_token_id": 50002,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:823842c4c3e89b3f8818717a803ec2bce7dc9d1c8acb6404b623630b9be12548
+size 157415409