Instructions to use LLM360/K2-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM360/K2-Chat with Transformers:

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

pipe = pipeline("text-generation", model="LLM360/K2-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLM360/K2-Chat")
model = AutoModelForCausalLM.from_pretrained("LLM360/K2-Chat")
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

vLLM

How to use LLM360/K2-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM360/K2-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM360/K2-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLM360/K2-Chat

SGLang

How to use LLM360/K2-Chat 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 "LLM360/K2-Chat" \
    --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": "LLM360/K2-Chat",
		"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 "LLM360/K2-Chat" \
        --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": "LLM360/K2-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLM360/K2-Chat with Docker Model Runner:
```
docker model run hf.co/LLM360/K2-Chat
```

mylibrar commited on May 31, 2024

Commit

aaf824f

verified ·

1 Parent(s): fa4fcfb

Upload tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +11 -28
tokenizer.json +2 -29
tokenizer_config.json +2 -0

special_tokens_map.json CHANGED Viewed

@@ -1,34 +1,17 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|endofsystemprompt|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|beginofsystem|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|beginofuser|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|endofchat|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
   ],
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

 {
   "additional_special_tokens": [
+    "<|endofsystemprompt|>",
+    "<|beginofsystem|>",
+    "<|beginofuser|>",
+    "<|endofchat|>"
   ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json CHANGED Viewed

@@ -249,12 +249,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -263,24 +257,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -288,17 +270,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
   },
   "decoder": {
     "type": "Sequence",
@@ -332,6 +304,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
       {
         "Sequence": {
           "id": "A",
       }
     ],
     "pair": [
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
       {
         "Sequence": {
           "id": "B",
         }
       }
     ],
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json CHANGED Viewed

@@ -210,8 +210,10 @@
     "<|endofchat|>"
   ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 8192,
   "pad_token": null,
   "sp_model_kwargs": {},

     "<|endofchat|>"
   ],
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|beginofuser|>' + message['content'] }}{% elif message['role'] == 'system' %}{{ message['content'] + '<|endofsystemprompt|>' }}{% elif message['role'] == 'assistant' %}{{ '<|beginofsystem|>' + message['content'] }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|beginofsystem|>' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "legacy": true,
   "model_max_length": 8192,
   "pad_token": null,
   "sp_model_kwargs": {},