perlthoughts
commited on
Commit
•
fe032bc
1
Parent(s):
807fd2c
Upload MistralForCausalLM
Browse files- config.json +3 -3
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +1 -1
config.json
CHANGED
@@ -4,12 +4,12 @@
|
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
-
"eos_token_id":
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 14336,
|
12 |
-
"max_position_embeddings":
|
13 |
"model_type": "mistral",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
@@ -21,5 +21,5 @@
|
|
21 |
"torch_dtype": "float16",
|
22 |
"transformers_version": "4.35.2",
|
23 |
"use_cache": true,
|
24 |
-
"vocab_size":
|
25 |
}
|
|
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
"model_type": "mistral",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
|
|
21 |
"torch_dtype": "float16",
|
22 |
"transformers_version": "4.35.2",
|
23 |
"use_cache": true,
|
24 |
+
"vocab_size": 32000
|
25 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
-
"eos_token_id":
|
5 |
"transformers_version": "4.35.2"
|
6 |
}
|
|
|
1 |
{
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2df8b491cc63c0e64910f6d681b5f4d51f748219ecb9c15bed384879b2aea32
|
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 sha256:0824477a423500d46e6007ac17e97c77eb1832b2231d00578f64bdd5e152558b
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7168e0c199bae5d695f16eadff1e48c74a96e990780f6990ff9f14648b9ae1a8
|
3 |
+
size 4540516256
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|