rl-swarm: round 27854, agent foraging_docile_ibis
Browse files- README.md +2 -0
- config.json +29 -3
- generation_config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -9,6 +9,8 @@ tags:
|
|
| 9 |
- gensyn
|
| 10 |
- I am foraging docile ibis
|
| 11 |
- trl
|
|
|
|
|
|
|
| 12 |
licence: license
|
| 13 |
---
|
| 14 |
|
|
|
|
| 9 |
- gensyn
|
| 10 |
- I am foraging docile ibis
|
| 11 |
- trl
|
| 12 |
+
- genrl-swarm
|
| 13 |
+
- I am foraging_docile_ibis
|
| 14 |
licence: license
|
| 15 |
---
|
| 16 |
|
config.json
CHANGED
|
@@ -4,11 +4,38 @@
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
|
|
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 896,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 4864,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 32768,
|
| 13 |
"max_window_layers": 21,
|
| 14 |
"model_type": "qwen2",
|
|
@@ -18,10 +45,9 @@
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
"rope_scaling": null,
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
-
"sliding_window":
|
| 22 |
"tie_word_embeddings": true,
|
| 23 |
-
"
|
| 24 |
-
"transformers_version": "4.51.3",
|
| 25 |
"use_cache": true,
|
| 26 |
"use_sliding_window": false,
|
| 27 |
"vocab_size": 151936
|
|
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 896,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
"max_position_embeddings": 32768,
|
| 40 |
"max_window_layers": 21,
|
| 41 |
"model_type": "qwen2",
|
|
|
|
| 45 |
"rms_norm_eps": 1e-06,
|
| 46 |
"rope_scaling": null,
|
| 47 |
"rope_theta": 1000000.0,
|
| 48 |
+
"sliding_window": null,
|
| 49 |
"tie_word_embeddings": true,
|
| 50 |
+
"transformers_version": "4.56.1",
|
|
|
|
| 51 |
"use_cache": true,
|
| 52 |
"use_sliding_window": false,
|
| 53 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -10,5 +10,5 @@
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
-
"transformers_version": "4.
|
| 14 |
}
|
|
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.56.1"
|
| 14 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1976163472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d544759db94bb5153f3b10abad6cb528ea7288882e3fc183a6b802e3e72985dd
|
| 3 |
size 1976163472
|