Instructions to use themathys/mistralai-Code-Instruct-Finetune-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use themathys/mistralai-Code-Instruct-Finetune-test with Transformers:

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

pipe = pipeline("text-generation", model="themathys/mistralai-Code-Instruct-Finetune-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("themathys/mistralai-Code-Instruct-Finetune-test")
model = AutoModelForCausalLM.from_pretrained("themathys/mistralai-Code-Instruct-Finetune-test")
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 themathys/mistralai-Code-Instruct-Finetune-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/themathys/mistralai-Code-Instruct-Finetune-test

SGLang

How to use themathys/mistralai-Code-Instruct-Finetune-test 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 "themathys/mistralai-Code-Instruct-Finetune-test" \
    --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": "themathys/mistralai-Code-Instruct-Finetune-test",
		"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 "themathys/mistralai-Code-Instruct-Finetune-test" \
        --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": "themathys/mistralai-Code-Instruct-Finetune-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use themathys/mistralai-Code-Instruct-Finetune-test with Docker Model Runner:
```
docker model run hf.co/themathys/mistralai-Code-Instruct-Finetune-test
```

themathys commited on May 30, 2024

Commit

68e1591

verified ·

1 Parent(s): 3e4b9aa

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +1 -29
tokenizer_config.json +2 -2

tokenizer.json CHANGED Viewed

@@ -6953,12 +6953,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -6967,24 +6961,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -6992,17 +6974,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
   },
   "decoder": {
     "type": "Sequence",

   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
       {
         "Sequence": {
           "id": "A",
       }
     ],
     "pair": [
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
       {
         "Sequence": {
           "id": "B",
         }
       }
     ],
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "add_bos_token": true,
   "add_eos_token": false,
   "add_prefix_space": true,
   "added_tokens_decoder": {
@@ -6174,7 +6174,7 @@
   },
   "bos_token": "<s>",
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() + '' %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{{ bos_token }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{% set content = system_message + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + eos_token }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,

 {
+  "add_bos_token": false,
   "add_eos_token": false,
   "add_prefix_space": true,
   "added_tokens_decoder": {
   },
   "bos_token": "<s>",
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() + '' %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{{ bos_token }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 %}{% set content = system_message + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,