Upload LlamaForCausalLM
Browse files- config.json +7 -3
- model-00001-of-00008.safetensors +1 -1
- model-00002-of-00008.safetensors +1 -1
- model-00003-of-00008.safetensors +1 -1
- model-00004-of-00008.safetensors +1 -1
- model-00005-of-00008.safetensors +1 -1
- model-00006-of-00008.safetensors +1 -1
- model-00007-of-00008.safetensors +1 -1
- model-00008-of-00008.safetensors +1 -1
config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
|
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
@@ -11,10 +12,12 @@
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
"max_position_embeddings": 32768,
|
14 |
-
"
|
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
|
|
18 |
"quantization_config": {
|
19 |
"_load_in_4bit": false,
|
20 |
"_load_in_8bit": true,
|
@@ -31,6 +34,7 @@
|
|
31 |
"quant_method": "bitsandbytes"
|
32 |
},
|
33 |
"rms_norm_eps": 1e-05,
|
|
|
34 |
"rope_theta": 10000.0,
|
35 |
"sliding_window": 4096,
|
36 |
"tie_word_embeddings": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "filipealmeida/Mistral-7B-Instruct-v0.1-sharded",
|
3 |
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
],
|
6 |
+
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
"max_position_embeddings": 32768,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
+
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
"_load_in_4bit": false,
|
23 |
"_load_in_8bit": true,
|
|
|
34 |
"quant_method": "bitsandbytes"
|
35 |
},
|
36 |
"rms_norm_eps": 1e-05,
|
37 |
+
"rope_scaling": null,
|
38 |
"rope_theta": 10000.0,
|
39 |
"sliding_window": 4096,
|
40 |
"tie_word_embeddings": false,
|
model-00001-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 959013529
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7949455f9508d135cbe1bc99848906acb9a2c54c5cb7545fd9c83610570a1810
|
3 |
size 959013529
|
model-00002-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990734606
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:229dfd3d45680e7311b86814ba56ccd79444fecdc3a7bdafb2b2146426a5f5e9
|
3 |
size 990734606
|
model-00003-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 973917689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0537703366578e95233f2b1739c16c4cb6d52d3e18afbf6d36c0b5819f4d170
|
3 |
size 973917689
|
model-00004-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990734702
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2ffd4c801a5952f8c9a49734e52a5190acd52e57a26976ddbe8660b8669ee89
|
3 |
size 990734702
|
model-00005-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 973917737
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:785c2bf376b8373514c58f06c68b1de360aa26b460b6ce1d1e14462d8d2be5c2
|
3 |
size 973917737
|
model-00006-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990734702
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bc1cc8de30ae7f997457527d44665584dd3ab358c8c8d06c47a69fcadbd48bc
|
3 |
size 990734702
|
model-00007-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 973917737
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e0c7639876863715c071767c02830b40db6f31560962a8d344a56bb1aeecef4
|
3 |
size 973917737
|
model-00008-of-00008.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 656756538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf88a8c6d14134fe9950bf90b1b63e7fc4dc8e8e51d448bb3e2454359da70e39
|
3 |
size 656756538
|