update(weights): train rand init model for 5k steps on cosmopedia
Browse files- config.json +11 -8
- generation_config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,30 +1,33 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"StableLmForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
6 |
-
"bos_token_id":
|
7 |
-
"eos_token_id":
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_dropout": 0.0,
|
10 |
"hidden_size": 512,
|
11 |
-
"initializer_range": 0.
|
12 |
-
"intermediate_size":
|
13 |
"layer_norm_eps": 1e-05,
|
14 |
"max_position_embeddings": 4096,
|
15 |
"model_type": "stablelm",
|
16 |
"num_attention_heads": 16,
|
17 |
-
"num_hidden_layers":
|
18 |
-
"num_key_value_heads":
|
19 |
"partial_rotary_factor": 0.25,
|
20 |
"qk_layernorm": true,
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000,
|
|
|
23 |
"tie_word_embeddings": false,
|
24 |
-
"torch_dtype": "
|
25 |
"transformers_version": "4.39.0.dev0",
|
26 |
"use_cache": true,
|
|
|
27 |
"use_parallel_residual": true,
|
28 |
"use_qkv_bias": false,
|
29 |
-
"vocab_size":
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/weka2/home-guac/stable-lm/stable-neox/ckpts/stablelm_2_tiny/global_step6000",
|
3 |
"architectures": [
|
4 |
"StableLmForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 100257,
|
8 |
+
"eos_token_id": 100257,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_dropout": 0.0,
|
11 |
"hidden_size": 512,
|
12 |
+
"initializer_range": 0.01,
|
13 |
+
"intermediate_size": 1536,
|
14 |
"layer_norm_eps": 1e-05,
|
15 |
"max_position_embeddings": 4096,
|
16 |
"model_type": "stablelm",
|
17 |
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 8,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
"partial_rotary_factor": 0.25,
|
21 |
"qk_layernorm": true,
|
22 |
"rope_scaling": null,
|
23 |
"rope_theta": 10000,
|
24 |
+
"rotary_scaling_factor": 1.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.39.0.dev0",
|
28 |
"use_cache": true,
|
29 |
+
"use_norm_bias": false,
|
30 |
"use_parallel_residual": true,
|
31 |
"use_qkv_bias": false,
|
32 |
+
"vocab_size": 100352
|
33 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
"transformers_version": "4.39.0.dev0"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100257,
|
4 |
+
"eos_token_id": 100257,
|
5 |
"transformers_version": "4.39.0.dev0"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d04033878a589c26fea21e661a7f251d493790ac6bd595ad16a5834e6b17b5f
|
3 |
+
size 253811856
|