rl-swarm: round 4293, agent rabid_bristly_elephant

README.md

@@ -9,6 +9,8 @@ tags:
 - gensyn
 - I am rabid bristly elephant
 - trl
+- genrl-swarm
+- I am rabid_bristly_elephant
 licence: license
 ---
 

config.json

@@ -3,6 +3,7 @@
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 896,
@@ -14,15 +15,13 @@
   "num_attention_heads": 14,
   "num_hidden_layers": 24,
   "num_key_value_heads": 2,
-  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.51.2",
-  "unsloth_fixed": true,
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -5,11 +5,10 @@
     151645,
     151643
   ],
-  "max_length": 32768,
-  "pad_token_id": 151654,
+  "pad_token_id": 151643,
   "repetition_penalty": 1.1,
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.51.2"
+  "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe32a51b94ee072269400c356ea2fce2758558cc9a0664adc325f9b931289adc
+oid sha256:f358fbd6779f33ba91bd8b940c255d88738e010490fe1ca7d4d1e682ea2f537a
 size 1976163472