Instructions to use Ayansk11/FinSenti-MobileLLM-R1-950M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ayansk11/FinSenti-MobileLLM-R1-950M with Transformers:

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

pipe = pipeline("text-generation", model="Ayansk11/FinSenti-MobileLLM-R1-950M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ayansk11/FinSenti-MobileLLM-R1-950M")
model = AutoModelForCausalLM.from_pretrained("Ayansk11/FinSenti-MobileLLM-R1-950M")
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

vLLM

How to use Ayansk11/FinSenti-MobileLLM-R1-950M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ayansk11/FinSenti-MobileLLM-R1-950M"
# 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-MobileLLM-R1-950M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ayansk11/FinSenti-MobileLLM-R1-950M

SGLang

How to use Ayansk11/FinSenti-MobileLLM-R1-950M 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-MobileLLM-R1-950M" \
    --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-MobileLLM-R1-950M",
		"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-MobileLLM-R1-950M" \
        --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-MobileLLM-R1-950M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ayansk11/FinSenti-MobileLLM-R1-950M with Docker Model Runner:
```
docker model run hf.co/Ayansk11/FinSenti-MobileLLM-R1-950M
```

FinSenti-MobileLLM-R1-950M / config.json

Ayansk11

Upload folder using huggingface_hub

07bd760 verified 20 days ago

raw

history blame contribute delete

1.83 kB

	{
	"architectures": [
	"Llama4ForCausalLM"
	],
	"attention_bias": false,
	"attention_chunk_size": 32768,
	"attention_dropout": 0.0,
	"attn_scale": 0.1,
	"attn_temperature_tuning": false,
	"bos_token_id": 128000,
	"dtype": "bfloat16",
	"eos_token_id": [
	128001,
	128008,
	128009
	],
	"floor_scale": 8192,
	"for_llm_compressor": false,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 1536,
	"initializer_range": 0.02,
	"interleave_moe_layer_step": 0,
	"intermediate_size": 8192,
	"intermediate_size_mlp": 6144,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"model_type": "llama4_text",
	"moe_layers": [],
	"no_rope_layers": [
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1
	],
	"num_attention_heads": 24,
	"num_experts_per_tok": 0,
	"num_hidden_layers": 22,
	"num_key_value_heads": 6,
	"num_local_experts": 0,
	"output_router_logits": false,
	"pad_token_id": null,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 8000000.0,
	"rope_type": "default"
	},
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"tie_word_embeddings": true,
	"transformers_version": "5.2.0",
	"use_cache": true,
	"use_qk_norm": true,
	"vocab_size": 128257
	}