Upload folder using huggingface_hub
Browse files- README.md +1 -1
- config.json +2 -9
- model-00002-of-00005.safetensors +1 -1
- model-00003-of-00005.safetensors +1 -1
README.md
CHANGED
|
@@ -18,8 +18,8 @@ This model was merged using the Passthrough merge method.
|
|
| 18 |
### Models Merged
|
| 19 |
|
| 20 |
The following models were included in the merge:
|
| 21 |
-
* ./KansenSakura-RadianceV3-RP-12b
|
| 22 |
* ./rpmix
|
|
|
|
| 23 |
|
| 24 |
### Configuration
|
| 25 |
|
|
|
|
| 18 |
### Models Merged
|
| 19 |
|
| 20 |
The following models were included in the merge:
|
|
|
|
| 21 |
* ./rpmix
|
| 22 |
+
* ./KansenSakura-RadianceV3-RP-12b
|
| 23 |
|
| 24 |
### Configuration
|
| 25 |
|
config.json
CHANGED
|
@@ -4,13 +4,13 @@
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 1,
|
| 7 |
-
"eos_token_id":
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 14336,
|
| 13 |
-
"max_position_embeddings":
|
| 14 |
"model_type": "mistral",
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 40,
|
|
@@ -19,15 +19,8 @@
|
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
"sliding_window": null,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
-
"tokenizer": {
|
| 23 |
-
"add_bos_token": true,
|
| 24 |
-
"add_eos_token": false,
|
| 25 |
-
"pad_token": "</s>",
|
| 26 |
-
"padding_side": "right"
|
| 27 |
-
},
|
| 28 |
"torch_dtype": "bfloat16",
|
| 29 |
"transformers_version": "4.53.2",
|
| 30 |
-
"trust_remote_code": true,
|
| 31 |
"use_cache": false,
|
| 32 |
"vocab_size": 131072
|
| 33 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 1024000,
|
| 14 |
"model_type": "mistral",
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 40,
|
|
|
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
"sliding_window": null,
|
| 21 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"torch_dtype": "bfloat16",
|
| 23 |
"transformers_version": "4.53.2",
|
|
|
|
| 24 |
"use_cache": false,
|
| 25 |
"vocab_size": 131072
|
| 26 |
}
|
model-00002-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4907529456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:300f05ff84446a5f01db43b1fa590632e768b342a6f4c79a18a08842151eb88c
|
| 3 |
size 4907529456
|
model-00003-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4907529464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9db3481c766a85701e213155cb073f702c399410458368c7279344fc8e9b8717
|
| 3 |
size 4907529464
|