Instructions to use optimum-intel-internal-testing/tiny-GptOssForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use optimum-intel-internal-testing/tiny-GptOssForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="optimum-intel-internal-testing/tiny-GptOssForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("optimum-intel-internal-testing/tiny-GptOssForCausalLM")
model = AutoModelForCausalLM.from_pretrained("optimum-intel-internal-testing/tiny-GptOssForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use optimum-intel-internal-testing/tiny-GptOssForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "optimum-intel-internal-testing/tiny-GptOssForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "optimum-intel-internal-testing/tiny-GptOssForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/optimum-intel-internal-testing/tiny-GptOssForCausalLM

SGLang

How to use optimum-intel-internal-testing/tiny-GptOssForCausalLM 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 "optimum-intel-internal-testing/tiny-GptOssForCausalLM" \
    --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": "optimum-intel-internal-testing/tiny-GptOssForCausalLM",
		"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 "optimum-intel-internal-testing/tiny-GptOssForCausalLM" \
        --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": "optimum-intel-internal-testing/tiny-GptOssForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use optimum-intel-internal-testing/tiny-GptOssForCausalLM with Docker Model Runner:
```
docker model run hf.co/optimum-intel-internal-testing/tiny-GptOssForCausalLM
```

Re-upload config.json via AutoConfig (transformers 5.5)

by echarlaix HF Staff - opened 11 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-6

Files changed (1) hide show

config.json +8 -6

config.json CHANGED Viewed

@@ -4,7 +4,9 @@
   ],
   "attention_bias": true,
   "attention_dropout": 0.0,
   "dtype": "float32",
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 8,
@@ -23,21 +25,21 @@
   "num_key_value_heads": 2,
   "num_local_experts": 128,
   "output_router_logits": false,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
     "beta_fast": 32.0,
     "beta_slow": 1.0,
     "factor": 32.0,
     "original_max_position_embeddings": 4096,
     "rope_type": "yarn",
-    "truncate": false,
-    "rope_theta": 150000.0
   },
-  "rope_theta": 150000.0,
   "router_aux_loss_coef": 0.9,
   "sliding_window": 128,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "vocab_size": 200019
-}

   ],
   "attention_bias": true,
   "attention_dropout": 0.0,
+  "bos_token_id": null,
   "dtype": "float32",
+  "eos_token_id": null,
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 8,
   "num_key_value_heads": 2,
   "num_local_experts": 128,
   "output_router_logits": false,
+  "pad_token_id": null,
   "rms_norm_eps": 1e-05,
+  "rope_parameters": {
     "beta_fast": 32.0,
     "beta_slow": 1.0,
     "factor": 32.0,
     "original_max_position_embeddings": 4096,
+    "rope_theta": 150000.0,
     "rope_type": "yarn",
+    "truncate": false
   },
   "router_aux_loss_coef": 0.9,
   "sliding_window": 128,
   "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
   "use_cache": true,
   "vocab_size": 200019
+}