Commit
•
34e87cd
1
Parent(s):
51e7193
Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +2 -5
- model-00001-of-00002.safetensors +2 -2
- model.safetensors.index.json +1 -1
config.json
CHANGED
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 14336,
|
| 14 |
-
"max_position_embeddings":
|
| 15 |
"model_type": "llama",
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
|
@@ -30,10 +30,7 @@
|
|
| 30 |
"quant_method": "bitsandbytes"
|
| 31 |
},
|
| 32 |
"rms_norm_eps": 1e-05,
|
| 33 |
-
"rope_scaling":
|
| 34 |
-
"factor": 2.0,
|
| 35 |
-
"type": "linear"
|
| 36 |
-
},
|
| 37 |
"rope_theta": 500000.0,
|
| 38 |
"tie_word_embeddings": false,
|
| 39 |
"torch_dtype": "bfloat16",
|
|
|
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
"model_type": "llama",
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
|
|
|
| 30 |
"quant_method": "bitsandbytes"
|
| 31 |
},
|
| 32 |
"rms_norm_eps": 1e-05,
|
| 33 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
| 34 |
"rope_theta": 500000.0,
|
| 35 |
"tie_word_embeddings": false,
|
| 36 |
"torch_dtype": "bfloat16",
|
model-00001-of-00002.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 sha256:7db0be29385f1d39ba4d86fb9f18f8ff0081604f72afd49555f7eb0e5107067d
|
| 3 |
+
size 4652072924
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 5702577740
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|