RohanSardar/smolified-bengali-physics-teacher
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: RohanSardar/smolified-bengali-physics-teacher
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 08:37:37 +08:00
commit ee47a04dc5
7 changed files with 247 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
config.json Normal file
View File

@@ -0,0 +1,64 @@
{
"_sliding_window_pattern": 6,
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"torch_dtype": "bfloat16",
"eos_token_id": 106,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 640,
"initializer_range": 0.02,
"intermediate_size": 2048,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"model_name": "unsloth/gemma-3-270m-it",
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 18,
"num_key_value_heads": 1,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 512,
"tie_word_embeddings": true,
"unsloth_fixed": true,
"unsloth_version": "2026.3.11",
"use_bidirectional_attention": false,
"use_cache": false,
"vocab_size": 262144
}