Instructions to use Finnish-NLP/Ahma-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Finnish-NLP/Ahma-3B with Transformers:

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

pipe = pipeline("text-generation", model="Finnish-NLP/Ahma-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Finnish-NLP/Ahma-3B")
model = AutoModelForCausalLM.from_pretrained("Finnish-NLP/Ahma-3B", 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 Finnish-NLP/Ahma-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Finnish-NLP/Ahma-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Finnish-NLP/Ahma-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Finnish-NLP/Ahma-3B

SGLang

How to use Finnish-NLP/Ahma-3B 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 "Finnish-NLP/Ahma-3B" \
    --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": "Finnish-NLP/Ahma-3B",
		"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 "Finnish-NLP/Ahma-3B" \
        --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": "Finnish-NLP/Ahma-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Finnish-NLP/Ahma-3B with Docker Model Runner:
```
docker model run hf.co/Finnish-NLP/Ahma-3B
```

aapot commited on Jun 4, 2024

Commit

615b2a3

verified ·

1 Parent(s): ce7ff6d

fix autotokenizer

Browse files

Files changed (2) hide show

tokenizer.json +20 -9
tokenizer_config.json +5 -5

tokenizer.json CHANGED Viewed

@@ -37,7 +37,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
     },
     {
       "id": 4,
@@ -46,7 +46,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
     },
     {
       "id": 5,
@@ -55,7 +55,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
     },
     {
       "id": 6,
@@ -64,15 +64,26 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
     }
   ],
-  "normalizer": null,
   "pre_tokenizer": {
-    "type": "Metaspace",
-    "replacement": "▁",
-    "prepend_scheme": "first",
-    "split": false
   },
   "post_processor": {
     "type": "TemplateProcessing",

       "lstrip": false,
       "rstrip": false,
       "normalized": false,
+      "special": true
     },
     {
       "id": 4,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
+      "special": true
     },
     {
       "id": 5,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
+      "special": true
     },
     {
       "id": 6,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
+      "special": true
     }
   ],
+  "normalizer": {
+    "type": "Replace",
+    "pattern": {
+      "Regex": " {2,}"
+    },
+    "content": "▁"
+  },
   "pre_tokenizer": {
+    "type": "Sequence",
+    "pretokenizers": [
+      {
+        "type": "Metaspace",
+        "replacement": "▁",
+        "prepend_scheme": "first",
+        "split": false
+      }
+    ]
   },
   "post_processor": {
     "type": "TemplateProcessing",

tokenizer_config.json CHANGED Viewed

@@ -33,7 +33,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     },
     "4": {
       "content": "[/INST]",
@@ -41,7 +41,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     },
     "5": {
       "content": "<<SYS>>",
@@ -49,7 +49,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     },
     "6": {
       "content": "<</SYS>>",
@@ -57,7 +57,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
     }
   },
   "bos_token": "<s>",
@@ -69,7 +69,7 @@
   "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     },
     "4": {
       "content": "[/INST]",
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     },
     "5": {
       "content": "<<SYS>>",
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     },
     "6": {
       "content": "<</SYS>>",
       "normalized": false,
       "rstrip": false,
       "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<s>",
   "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }