Text Generation
Transformers
Safetensors
smollm3
Generated from Trainer
sft
hf_jobs
trl
conversational
Instructions to use Jake/SmolLM3-3B-MathSFT-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jake/SmolLM3-3B-MathSFT-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jake/SmolLM3-3B-MathSFT-v2") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jake/SmolLM3-3B-MathSFT-v2") model = AutoModelForCausalLM.from_pretrained("Jake/SmolLM3-3B-MathSFT-v2") 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 Jake/SmolLM3-3B-MathSFT-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jake/SmolLM3-3B-MathSFT-v2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jake/SmolLM3-3B-MathSFT-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Jake/SmolLM3-3B-MathSFT-v2
- SGLang
How to use Jake/SmolLM3-3B-MathSFT-v2 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 "Jake/SmolLM3-3B-MathSFT-v2" \ --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": "Jake/SmolLM3-3B-MathSFT-v2", "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 "Jake/SmolLM3-3B-MathSFT-v2" \ --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": "Jake/SmolLM3-3B-MathSFT-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Jake/SmolLM3-3B-MathSFT-v2 with Docker Model Runner:
docker model run hf.co/Jake/SmolLM3-3B-MathSFT-v2
Upload SmolLM3ForCausalLM
Browse files- config.json +111 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SmolLM3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 128012,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 65536,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mlp_bias": false,
|
| 55 |
+
"model_type": "smollm3",
|
| 56 |
+
"no_rope_layer_interval": 4,
|
| 57 |
+
"no_rope_layers": [
|
| 58 |
+
1,
|
| 59 |
+
1,
|
| 60 |
+
1,
|
| 61 |
+
0,
|
| 62 |
+
1,
|
| 63 |
+
1,
|
| 64 |
+
1,
|
| 65 |
+
0,
|
| 66 |
+
1,
|
| 67 |
+
1,
|
| 68 |
+
1,
|
| 69 |
+
0,
|
| 70 |
+
1,
|
| 71 |
+
1,
|
| 72 |
+
1,
|
| 73 |
+
0,
|
| 74 |
+
1,
|
| 75 |
+
1,
|
| 76 |
+
1,
|
| 77 |
+
0,
|
| 78 |
+
1,
|
| 79 |
+
1,
|
| 80 |
+
1,
|
| 81 |
+
0,
|
| 82 |
+
1,
|
| 83 |
+
1,
|
| 84 |
+
1,
|
| 85 |
+
0,
|
| 86 |
+
1,
|
| 87 |
+
1,
|
| 88 |
+
1,
|
| 89 |
+
0,
|
| 90 |
+
1,
|
| 91 |
+
1,
|
| 92 |
+
1,
|
| 93 |
+
0
|
| 94 |
+
],
|
| 95 |
+
"num_attention_heads": 16,
|
| 96 |
+
"num_hidden_layers": 36,
|
| 97 |
+
"num_key_value_heads": 4,
|
| 98 |
+
"pad_token_id": 128012,
|
| 99 |
+
"pretraining_tp": 1,
|
| 100 |
+
"rms_norm_eps": 1e-06,
|
| 101 |
+
"rope_parameters": {
|
| 102 |
+
"rope_theta": 5000000.0,
|
| 103 |
+
"rope_type": "default"
|
| 104 |
+
},
|
| 105 |
+
"sliding_window": null,
|
| 106 |
+
"tie_word_embeddings": true,
|
| 107 |
+
"transformers_version": "5.3.0",
|
| 108 |
+
"use_cache": false,
|
| 109 |
+
"use_sliding_window": false,
|
| 110 |
+
"vocab_size": 128256
|
| 111 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
128012
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 128012,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.95,
|
| 9 |
+
"transformers_version": "5.3.0"
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:803ae0a1c18b636e1850b5737289b641aa76287cace6aeff8ef26dd9ddcd3f5c
|
| 3 |
+
size 6150235096
|