Upload MistralForCausalLM
Browse files- config.json +3 -3
- 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 |
],
|
|
@@ -16,8 +16,8 @@
|
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
-
"rope_theta":
|
| 20 |
-
"sliding_window":
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.36.2",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "NurtureAI/OpenHermes-2.5-Mistral-7B-16k",
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
|
|
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 100000.0,
|
| 20 |
+
"sliding_window": 16384,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.36.2",
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4943178624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4068edfdb584a431bb9a9d5208e859ab39fcf25d36fc5394387ec72b2784557
|
| 3 |
size 4943178624
|
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 sha256:72c26a71340901f2211c373cd6886d083855950b046aca5a3cd25761f59650c1
|
| 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 4540532640
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:806d1e62090e0073154f82326981a7619e2e0565bfd3c235aff31d340b6d21fb
|
| 3 |
size 4540532640
|