Instructions to use amd/Instella-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/Instella-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="amd/Instella-3B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("amd/Instella-3B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use amd/Instella-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Instella-3B-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": "amd/Instella-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/Instella-3B-Instruct

SGLang

How to use amd/Instella-3B-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 "amd/Instella-3B-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": "amd/Instella-3B-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 "amd/Instella-3B-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": "amd/Instella-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/Instella-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/amd/Instella-3B-Instruct
```

Prakamya commited on Mar 28, 2025

Commit

bd58f9f

1 Parent(s): e02fbea

Update tokenizer files

Browse files

Files changed (2) hide show

tokenizer.json +1 -10
tokenizer_config.json +2 -9

tokenizer.json CHANGED Viewed

@@ -254,15 +254,6 @@
       "rstrip": false,
       "normalized": true,
       "special": false
-    },
-    {
-      "id": 50280,
-      "content": "<padding>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {
@@ -250610,4 +250601,4 @@
       ]
     ]
   }
-}

       "rstrip": false,
       "normalized": true,
       "special": false
     }
   ],
   "normalizer": {
       ]
     ]
   }
+}

tokenizer_config.json CHANGED Viewed

@@ -226,14 +226,6 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "50280": {
-      "content": "<|padding|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
@@ -242,7 +234,8 @@
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<padding>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

       "rstrip": false,
       "single_word": false,
       "special": false
     }
   },
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }