Upload MistralForCausalLM
Browse files- config.json +4 -6
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
@@ -15,14 +15,12 @@
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
-
"pad_token_id": 2,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
-
"rope_theta":
|
21 |
-
"sliding_window":
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "float16",
|
24 |
-
"transformers_version": "4.
|
25 |
-
"unsloth_version": "2024.1",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "chanwit/flux-base-optimized",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
|
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.35.2",
|
|
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.35.2"
|
6 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b00c2d520ae75de22cc5b7ec31506da3516ccb1e11bfd49c5e438d315746cd9
|
3 |
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c1c1b41301a2fb30008e4784b73fafaf484fa992c7f9e37e23a5e58eed47edf
|
3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfc66dc9d8105a8f687dd7d6db042f8ee304719c4485456203e0fceca4370302
|
3 |
size 4540516256
|