Instructions to use nagrajn/TinyLinux3B_msphi3_Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nagrajn/TinyLinux3B_msphi3_Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nagrajn/TinyLinux3B_msphi3_Instruct", 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("nagrajn/TinyLinux3B_msphi3_Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nagrajn/TinyLinux3B_msphi3_Instruct", trust_remote_code=True, device_map="auto")
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 nagrajn/TinyLinux3B_msphi3_Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nagrajn/TinyLinux3B_msphi3_Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nagrajn/TinyLinux3B_msphi3_Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nagrajn/TinyLinux3B_msphi3_Instruct

SGLang

How to use nagrajn/TinyLinux3B_msphi3_Instruct 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 "nagrajn/TinyLinux3B_msphi3_Instruct" \
    --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": "nagrajn/TinyLinux3B_msphi3_Instruct",
		"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 "nagrajn/TinyLinux3B_msphi3_Instruct" \
        --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": "nagrajn/TinyLinux3B_msphi3_Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nagrajn/TinyLinux3B_msphi3_Instruct with Docker Model Runner:
```
docker model run hf.co/nagrajn/TinyLinux3B_msphi3_Instruct
```

nagrajn commited on Jul 28, 2024

Commit

3e4395b

verified ·

1 Parent(s): 9f9a2a3

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +0 -27
tokenizer_config.json +3 -2

tokenizer.json CHANGED Viewed

@@ -155,12 +155,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -175,12 +169,6 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -193,12 +181,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -213,15 +195,6 @@
       }
     ],
     "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      },
       "<|endoftext|>": {
         "id": "<|endoftext|>",
         "ids": [

   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
       {
         "Sequence": {
           "id": "A",
       }
     ],
     "pair": [
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
       {
         "Sequence": {
           "id": "B",
       }
     ],
     "special_tokens": {
       "<|endoftext|>": {
         "id": "<|endoftext|>",
         "ids": [

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,7 @@
 {
-  "add_bos_token": true,
   "add_eos_token": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -116,7 +117,7 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,

 {
+  "add_bos_token": false,
   "add_eos_token": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,