Instructions to use Ayansk11/FinSenti-Tiny-LLM-10M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ayansk11/FinSenti-Tiny-LLM-10M with Transformers:

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

pipe = pipeline("text-generation", model="Ayansk11/FinSenti-Tiny-LLM-10M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ayansk11/FinSenti-Tiny-LLM-10M")
model = AutoModelForCausalLM.from_pretrained("Ayansk11/FinSenti-Tiny-LLM-10M", 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 Ayansk11/FinSenti-Tiny-LLM-10M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ayansk11/FinSenti-Tiny-LLM-10M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ayansk11/FinSenti-Tiny-LLM-10M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ayansk11/FinSenti-Tiny-LLM-10M

SGLang

How to use Ayansk11/FinSenti-Tiny-LLM-10M 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 "Ayansk11/FinSenti-Tiny-LLM-10M" \
    --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": "Ayansk11/FinSenti-Tiny-LLM-10M",
		"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 "Ayansk11/FinSenti-Tiny-LLM-10M" \
        --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": "Ayansk11/FinSenti-Tiny-LLM-10M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ayansk11/FinSenti-Tiny-LLM-10M with Docker Model Runner:
```
docker model run hf.co/Ayansk11/FinSenti-Tiny-LLM-10M
```

Ayansk11 commited on May 30

Commit

506bcc4

verified ·

1 Parent(s): a4b9562

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

chat_template.jinja +8 -2
config.json +2 -2
generation_config.json +4 -1
model.safetensors +1 -1

chat_template.jinja CHANGED Viewed

@@ -1,5 +1,11 @@
-{% for message in messages %}<|header_start|>{{ message['role'] }}<|header_end|>
-{{ message['content'] }}<|eot|>{% endfor %}{% if add_generation_prompt %}<|header_start|>assistant<|header_end|>
 {% endif %}

+{% for message in messages %}{% if message['role'] == 'system' %}### System
+{{ message['content'] }}
+{% elif message['role'] == 'user' %}### Input
+{{ message['content'] }}
+{% elif message['role'] == 'assistant' %}### Response
+{{ message['content'] }}{{ eos_token }}
+{% endif %}{% endfor %}{% if add_generation_prompt %}### Response
 {% endif %}

config.json CHANGED Viewed

@@ -18,7 +18,7 @@
   "num_attention_heads": 2,
   "num_hidden_layers": 1,
   "num_key_value_heads": 1,
-  "pad_token_id": null,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_parameters": {
@@ -27,6 +27,6 @@
   },
   "tie_word_embeddings": false,
   "transformers_version": "5.2.0",
-  "use_cache": true,
   "vocab_size": 32001
 }

   "num_attention_heads": 2,
   "num_hidden_layers": 1,
   "num_key_value_heads": 1,
+  "pad_token_id": 32000,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_parameters": {
   },
   "tie_word_embeddings": false,
   "transformers_version": "5.2.0",
+  "use_cache": false,
   "vocab_size": 32001
 }

generation_config.json CHANGED Viewed

@@ -1,7 +1,10 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
   "tie_word_embeddings": false,
   "transformers_version": "5.2.0",
   "use_cache": true

 {
   "_from_model_config": true,
   "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 32000,
   "tie_word_embeddings": false,
   "transformers_version": "5.2.0",
   "use_cache": true

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad00b2836e7f6234f55f99d6fa2e64d64c2d44e9a1e6c2c13c937dabf191c623
 size 25980048

 version https://git-lfs.github.com/spec/v1
+oid sha256:aaa18c0d8276b37da5779089b1b3b24a0041f345b2594216e4390aa5438f8161
 size 25980048