b7b7a8a3fa
Model: ermiaazarkhalili/Granite-4.1-3B-SFT-Claude-Opus-Reasoning-Unsloth Source: Original Platform
35 lines
949 B
JSON
35 lines
949 B
JSON
{
|
|
"architectures": [
|
|
"GraniteForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attention_multiplier": 0.015625,
|
|
"bos_token_id": 100257,
|
|
"torch_dtype": "bfloat16",
|
|
"embedding_multiplier": 12.0,
|
|
"eos_token_id": 100257,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2560,
|
|
"initializer_range": 0.1,
|
|
"intermediate_size": 8192,
|
|
"logits_scaling": 10.0,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_name": "ibm-granite/granite-4.1-3b",
|
|
"model_type": "granite",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 100256,
|
|
"residual_multiplier": 0.22,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_parameters": {
|
|
"rope_theta": 10000000,
|
|
"rope_type": "default"
|
|
},
|
|
"tie_word_embeddings": true,
|
|
"unsloth_version": "2026.4.6",
|
|
"use_cache": false,
|
|
"vocab_size": 100352
|
|
} |