Upload folder using huggingface_hub
Browse files- config.json +3 -3
- generation_config.json +2 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- trainer_state.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 128000,
|
|
|
|
| 8 |
"eos_token_id": [
|
| 9 |
128001,
|
| 10 |
128008,
|
|
@@ -32,8 +33,7 @@
|
|
| 32 |
},
|
| 33 |
"rope_theta": 500000.0,
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
-
"
|
| 36 |
-
"transformers_version": "4.55.0",
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 128256
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"LlamaWithIntervention"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 128000,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
"eos_token_id": [
|
| 10 |
128001,
|
| 11 |
128008,
|
|
|
|
| 33 |
},
|
| 34 |
"rope_theta": 500000.0,
|
| 35 |
"tie_word_embeddings": false,
|
| 36 |
+
"transformers_version": "4.56.2",
|
|
|
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 128256
|
| 39 |
}
|
generation_config.json
CHANGED
|
@@ -7,6 +7,7 @@
|
|
| 7 |
128008,
|
| 8 |
128009
|
| 9 |
],
|
|
|
|
| 10 |
"sae_layers": null,
|
| 11 |
"sae_weights_path": null,
|
| 12 |
"special_tokens_ids": {
|
|
@@ -18,6 +19,6 @@
|
|
| 18 |
"target_model_layers": 32,
|
| 19 |
"temperature": 0.6,
|
| 20 |
"top_p": 0.9,
|
| 21 |
-
"transformers_version": "4.
|
| 22 |
"use_embed_proj": false
|
| 23 |
}
|
|
|
|
| 7 |
128008,
|
| 8 |
128009
|
| 9 |
],
|
| 10 |
+
"num_continuous_generation_layers": 0,
|
| 11 |
"sae_layers": null,
|
| 12 |
"sae_weights_path": null,
|
| 13 |
"special_tokens_ids": {
|
|
|
|
| 19 |
"target_model_layers": 32,
|
| 20 |
"temperature": 0.6,
|
| 21 |
"top_p": 0.9,
|
| 22 |
+
"transformers_version": "4.56.2",
|
| 23 |
"use_embed_proj": false
|
| 24 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9262f27ef21d971e0e0d2c2b614b7b2888cb443f8c609160c03aa14150f9b4aa
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c9f7780421d306e19aed8e279c1f7e604f7f5f115bd6ab3760dbbf0fb6829a5
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45e86f89d1fa8628d2863deb63b2b15ca9e68d4a154cce1117397c91e742d635
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b7920ea88333700cee6fb31f7ce59d9e67869ca580818ca64ef80583db2266c
|
| 3 |
size 1168138808
|
rng_state.pth
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 sha256:7bc64fee40bc84a2f39b2a767c18218cc72f16707e69c98cda4d445fdd30162c
|
| 3 |
+
size 14581
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00de011c95e1dc7d68afabfdfa928636db55405cacf169ada803d8170cbc280b
|
| 3 |
size 1465
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
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 sha256:62f4946b48d158517b3a939b70ba90001642272ff77805691cc0e36e627547a5
|
| 3 |
+
size 5905
|