rl-swarm: round 4291, agent sly_nimble_lemur
Browse files- README.md +2 -0
- config.json +3 -4
- generation_config.json +2 -3
- model.safetensors +1 -1
README.md
CHANGED
@@ -9,6 +9,8 @@ tags:
|
|
9 |
- gensyn
|
10 |
- I am sly nimble lemur
|
11 |
- trl
|
|
|
|
|
12 |
licence: license
|
13 |
---
|
14 |
|
|
|
9 |
- gensyn
|
10 |
- I am sly nimble lemur
|
11 |
- trl
|
12 |
+
- genrl-swarm
|
13 |
+
- I am sly_nimble_lemur
|
14 |
licence: license
|
15 |
---
|
16 |
|
config.json
CHANGED
@@ -3,6 +3,7 @@
|
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
|
|
6 |
"eos_token_id": 151645,
|
7 |
"hidden_act": "silu",
|
8 |
"hidden_size": 896,
|
@@ -14,15 +15,13 @@
|
|
14 |
"num_attention_heads": 14,
|
15 |
"num_hidden_layers": 24,
|
16 |
"num_key_value_heads": 2,
|
17 |
-
"pad_token_id": 151654,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_scaling": null,
|
20 |
"rope_theta": 1000000.0,
|
21 |
-
"sliding_window":
|
22 |
"tie_word_embeddings": true,
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.51.
|
25 |
-
"unsloth_fixed": true,
|
26 |
"use_cache": true,
|
27 |
"use_sliding_window": false,
|
28 |
"vocab_size": 151936
|
|
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
"eos_token_id": 151645,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 896,
|
|
|
15 |
"num_attention_heads": 14,
|
16 |
"num_hidden_layers": 24,
|
17 |
"num_key_value_heads": 2,
|
|
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_scaling": null,
|
20 |
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": 32768,
|
22 |
"tie_word_embeddings": true,
|
23 |
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.51.3",
|
|
|
25 |
"use_cache": true,
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 151936
|
generation_config.json
CHANGED
@@ -5,11 +5,10 @@
|
|
5 |
151645,
|
6 |
151643
|
7 |
],
|
8 |
-
"
|
9 |
-
"pad_token_id": 151654,
|
10 |
"repetition_penalty": 1.1,
|
11 |
"temperature": 0.7,
|
12 |
"top_k": 20,
|
13 |
"top_p": 0.8,
|
14 |
-
"transformers_version": "4.51.
|
15 |
}
|
|
|
5 |
151645,
|
6 |
151643
|
7 |
],
|
8 |
+
"pad_token_id": 151643,
|
|
|
9 |
"repetition_penalty": 1.1,
|
10 |
"temperature": 0.7,
|
11 |
"top_k": 20,
|
12 |
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.51.3"
|
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 sha256:301ede62fb4b8b86c72e31205c56424756cf9f3440607f1adcdd7ee2bd2fee52
|
3 |
size 1976163472
|