Training in progress, step 80
Browse files- adapter_model.safetensors +1 -1
- config.json +19 -24
- model.safetensors +1 -1
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 139512976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ad97159c3b42a1f905ccc4485d0017d16328da85c17552c4431ff940c5802b4
|
| 3 |
size 139512976
|
config.json
CHANGED
|
@@ -1,36 +1,31 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
},
|
| 11 |
-
"bos_token_id": 1,
|
| 12 |
-
"embd_pdrop": 0.0,
|
| 13 |
-
"eos_token_id": 32000,
|
| 14 |
"hidden_act": "silu",
|
| 15 |
-
"hidden_size":
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size":
|
| 18 |
-
"max_position_embeddings":
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"pad_token_id":
|
| 25 |
-
"
|
| 26 |
-
"resid_pdrop": 0.0,
|
| 27 |
-
"rms_norm_eps": 1e-05,
|
| 28 |
"rope_scaling": null,
|
| 29 |
-
"rope_theta":
|
| 30 |
-
"sliding_window":
|
| 31 |
-
"tie_word_embeddings":
|
| 32 |
"torch_dtype": "float32",
|
| 33 |
"transformers_version": "4.51.3",
|
| 34 |
"use_cache": true,
|
| 35 |
-
"
|
|
|
|
| 36 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 151643,
|
| 21 |
+
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
| 22 |
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 1000000,
|
| 24 |
+
"sliding_window": null,
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
"torch_dtype": "float32",
|
| 27 |
"transformers_version": "4.51.3",
|
| 28 |
"use_cache": true,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:107cc08a9f2982f3af34a2297184ffa22006a938a420d03a33a44a6ba59d7d28
|
| 3 |
size 2384234968
|