Instructions to use HuggingFaceM4/tiny-random-vllama-clip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/tiny-random-vllama-clip with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceM4/tiny-random-vllama-clip")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/tiny-random-vllama-clip", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/tiny-random-vllama-clip with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/tiny-random-vllama-clip"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/tiny-random-vllama-clip",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/tiny-random-vllama-clip

SGLang

How to use HuggingFaceM4/tiny-random-vllama-clip 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 "HuggingFaceM4/tiny-random-vllama-clip" \
    --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": "HuggingFaceM4/tiny-random-vllama-clip",
		"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 "HuggingFaceM4/tiny-random-vllama-clip" \
        --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": "HuggingFaceM4/tiny-random-vllama-clip",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/tiny-random-vllama-clip with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/tiny-random-vllama-clip
```

VictorSanh commited on Apr 25, 2023

Commit

6c6acc8

1 Parent(s): c8c498d

update model with latest tokenizer

Browse files

Files changed (3) hide show

config.json +3 -4
generation_config.json +1 -1
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "tiny-random-vllama-clip",
   "additional_vocab_size": 2,
   "alpha_initializer": "ones",
   "alpha_type": "vector",
@@ -24,7 +23,7 @@
   "intermediate_size": 11008,
   "max_new_tokens": 100,
   "max_position_embeddings": 128,
-  "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "pad_token_id": 0,
@@ -36,8 +35,8 @@
   "resampler_n_latents": 16,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.0.dev0",
   "use_cache": true,
   "use_resampler": true,
   "vision_embed_dim": 32,

 {
   "additional_vocab_size": 2,
   "alpha_initializer": "ones",
   "alpha_type": "vector",
   "intermediate_size": 11008,
   "max_new_tokens": 100,
   "max_position_embeddings": 128,
+  "model_type": "vllama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "resampler_n_latents": 16,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.0.dev0",
   "use_cache": true,
   "use_resampler": true,
   "vision_embed_dim": 32,

generation_config.json CHANGED Viewed

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "max_new_tokens": 100,
   "pad_token_id": 0,
-  "transformers_version": "4.28.0.dev0"
 }

   "eos_token_id": 2,
   "max_new_tokens": 100,
   "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b12743cfed7632ce36846850750c4c874dba173638e1d85c1d1e03b74c1610
-size 12878457

 version https://git-lfs.github.com/spec/v1
+oid sha256:b6f5de05e77b318f3a80f79e1a8d6b1eda26841ecfd9c0afc4c38a2d14b4e6a5
+size 6467421