Instructions to use EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml with Transformers:

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

pipe = pipeline("text-generation", model="EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml

SGLang

How to use EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml 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 "EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml" \
    --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": "EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml",
		"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 "EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml" \
        --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": "EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml with Docker Model Runner:
```
docker model run hf.co/EmbeddedLLM/llama-2-13b-chat-int4-onnx-directml
```

tjellm commited on Jun 16, 2024

Commit

3e1bc15

verified ·

1 Parent(s): 68b611c

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

.gitattributes +1 -0
genai_config.json +54 -0
model.onnx +3 -0
model.onnx.data +3 -0
special_tokens_map.json +23 -0
tokenizer.json +0 -0
tokenizer_config.json +41 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.onnx.data filter=lfs diff=lfs merge=lfs -text

genai_config.json ADDED Viewed

	@@ -0,0 +1,54 @@

+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 4096,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "dml": {}
+                    }
+                ]
+            },
+            "filename": "model.onnx",
+            "head_size": 128,
+            "hidden_size": 5120,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "position_ids": "position_ids",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 40,
+            "num_hidden_layers": 40,
+            "num_key_value_heads": 40
+        },
+        "eos_token_id": 2,
+        "pad_token_id": 0,
+        "type": "llama",
+        "vocab_size": 32000
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": true,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 4096,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 0.6,
+        "top_k": 1,
+        "top_p": 0.9
+    }
+}

model.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:72e9189e3b8d77602943d82413ad7a106d1ef21d929a59dfe33cb55daf273f27
+size 343788

model.onnx.data ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6950764c48bfd31e8d911f7857bec3802f8b845b50bec1e3b7240a7312ff69
+size 7558588416

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,23 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}