Instructions to use unsloth/Mistral-Nemo-Base-2407 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Mistral-Nemo-Base-2407 with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Mistral-Nemo-Base-2407")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Mistral-Nemo-Base-2407")
model = AutoModelForCausalLM.from_pretrained("unsloth/Mistral-Nemo-Base-2407", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/Mistral-Nemo-Base-2407 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Mistral-Nemo-Base-2407"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Mistral-Nemo-Base-2407",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/Mistral-Nemo-Base-2407

SGLang

How to use unsloth/Mistral-Nemo-Base-2407 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 "unsloth/Mistral-Nemo-Base-2407" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Mistral-Nemo-Base-2407",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "unsloth/Mistral-Nemo-Base-2407" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Mistral-Nemo-Base-2407",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use unsloth/Mistral-Nemo-Base-2407 with Docker Model Runner:
```
docker model run hf.co/unsloth/Mistral-Nemo-Base-2407
```

danielhanchen commited on Jul 19, 2024

Commit

e3e20c3

verified ·

1 Parent(s): d42942a

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +0 -18
tokenizer_config.json +2 -0

tokenizer.json CHANGED Viewed

@@ -9038,12 +9038,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -9059,12 +9053,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -9076,12 +9064,6 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {

           "id": "A",
           "type_id": 0
         }
       }
     ],
     "pair": [
           "type_id": 0
         }
       },
       {
         "SpecialToken": {
           "id": "<s>",
           "id": "B",
           "type_id": 1
         }
       }
     ],
     "special_tokens": {

tokenizer_config.json CHANGED Viewed

@@ -1,4 +1,6 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {

 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {