0xgr3y/Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tall_tame_panther
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

rl-swarm: round 12817, agent tall_tame_panther

Browse Source
This commit is contained in:
grey
2025-11-13 08:43:00 +00:00
committed by system
parent 18a23675d7
commit 18ec009a36
4 changed files with 275 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
config.json Normal file
View File

@@ -0,0 +1,54 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"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",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}