Upload merged model from checkpoint-6250 (Trained with Unsloth)
Browse files- README.md +1 -0
- config.json +3 -1
- generation_config.json +2 -0
- model-00001-of-00005.safetensors +2 -2
- model-00002-of-00005.safetensors +2 -2
- model-00003-of-00005.safetensors +2 -2
- model-00004-of-00005.safetensors +2 -2
- model-00005-of-00005.safetensors +2 -2
README.md
CHANGED
|
@@ -11,6 +11,7 @@ tags:
|
|
| 11 |
- merged
|
| 12 |
- bilingual
|
| 13 |
- visionspace
|
|
|
|
| 14 |
library_name: transformers
|
| 15 |
pipeline_tag: text-generation
|
| 16 |
---
|
|
|
|
| 11 |
- merged
|
| 12 |
- bilingual
|
| 13 |
- visionspace
|
| 14 |
+
- unsloth
|
| 15 |
library_name: transformers
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
---
|
config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
-
"dtype": "
|
| 9 |
"eos_token_id": 32000,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
|
@@ -18,12 +18,14 @@
|
|
| 18 |
"num_attention_heads": 32,
|
| 19 |
"num_hidden_layers": 48,
|
| 20 |
"num_key_value_heads": 8,
|
|
|
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
"rope_scaling": null,
|
| 24 |
"rope_theta": 10000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"transformers_version": "4.56.2",
|
|
|
|
| 27 |
"use_cache": false,
|
| 28 |
"vocab_size": 40960
|
| 29 |
}
|
|
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
"eos_token_id": 32000,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
|
|
|
| 18 |
"num_attention_heads": 32,
|
| 19 |
"num_hidden_layers": 48,
|
| 20 |
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 2,
|
| 22 |
"pretraining_tp": 1,
|
| 23 |
"rms_norm_eps": 1e-05,
|
| 24 |
"rope_scaling": null,
|
| 25 |
"rope_theta": 10000.0,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"transformers_version": "4.56.2",
|
| 28 |
+
"unsloth_version": "2025.10.1",
|
| 29 |
"use_cache": false,
|
| 30 |
"vocab_size": 40960
|
| 31 |
}
|
generation_config.json
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 32000,
|
|
|
|
|
|
|
| 5 |
"transformers_version": "4.56.2",
|
| 6 |
"use_cache": false
|
| 7 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 32000,
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"pad_token_id": 2,
|
| 7 |
"transformers_version": "4.56.2",
|
| 8 |
"use_cache": false
|
| 9 |
}
|
model-00001-of-00005.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:e48c9ea606fa1c1a192ab4f44d2f9fd750c282ddcc6a95807d6fd4dc9fed0a56
|
| 3 |
+
size 4899122032
|
model-00002-of-00005.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:bff33c477e4b4352f1a0013324a17b4446a9c496d2e6eac7d894d22a8946f33e
|
| 3 |
+
size 4915916176
|
model-00003-of-00005.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:cd6b03b8bbbb794a955e4756118d39ccbc938d4db3d86408951f5388c01d53a5
|
| 3 |
+
size 4999819336
|
model-00004-of-00005.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 sha256:79a9ac582ed87cb2e2fe35786446778fecdbee8e78ba1185166c45de476a2730
|
| 3 |
+
size 4915916184
|
model-00005-of-00005.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 sha256:9b002e399f31a580416e42968f51bc59556f5610d3329c1a398d90949ba7cd64
|
| 3 |
+
size 1879125728
|