Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-e2-bs8
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: Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-e2-bs8
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-24 19:31:08 +08:00
commit 5a3f6279d8
11 changed files with 2293 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
config.json Normal file
View File

@@ -0,0 +1,76 @@
{
"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": 128009,
"floor_scale": 8192,
"for_llm_compressor": false,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 576,
"initializer_range": 0.02,
"interleave_moe_layer_step": 0,
"intermediate_size": 8192,
"intermediate_size_mlp": 2048,
"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"
],
"max_position_embeddings": 4096,
"model_type": "llama4_text",
"moe_layers": [],
"no_rope_layers": [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
],
"num_attention_heads": 9,
"num_experts_per_tok": 0,
"num_hidden_layers": 15,
"num_key_value_heads": 3,
"num_local_experts": 0,
"output_router_logits": false,
"pad_token_id": 128009,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": false,
"use_qk_norm": true,
"vocab_size": 128256
}