Checkpoint at step 66000
Browse files
checkpoint-66000/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 3,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 3,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 512,
|
| 13 |
+
"initializer_range": 0.041666666666666664,
|
| 14 |
+
"intermediate_size": 2304,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention"
|
| 33 |
+
],
|
| 34 |
+
"max_position_embeddings": 1024,
|
| 35 |
+
"max_window_layers": 17,
|
| 36 |
+
"model_type": "qwen3",
|
| 37 |
+
"num_attention_heads": 4,
|
| 38 |
+
"num_hidden_layers": 17,
|
| 39 |
+
"num_key_value_heads": 1,
|
| 40 |
+
"pad_token_id": null,
|
| 41 |
+
"rms_norm_eps": 1e-06,
|
| 42 |
+
"rope_parameters": {
|
| 43 |
+
"rope_theta": 10000,
|
| 44 |
+
"rope_type": "default"
|
| 45 |
+
},
|
| 46 |
+
"sliding_window": null,
|
| 47 |
+
"tie_word_embeddings": false,
|
| 48 |
+
"transformers_version": "5.0.0",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"use_sliding_window": false,
|
| 51 |
+
"vocab_size": 23947
|
| 52 |
+
}
|
checkpoint-66000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 3,
|
| 4 |
+
"eos_token_id": 3,
|
| 5 |
+
"transformers_version": "5.0.0"
|
| 6 |
+
}
|
checkpoint-66000/metadata.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b5882bea49dbf48e22eb925f85a04c8a2f40a37a4455368eb878ebe1e451df8
|
| 3 |
+
size 1331
|
checkpoint-66000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dd20c01d93e056165b56d699ef7685e1b2718c4f389e79cdfa38bd8811b8275
|
| 3 |
+
size 383409712
|
checkpoint-66000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c908938df359a77f5931c2cd4ef3173363f54bc5ad719f1473e4e99bc3e65ab3
|
| 3 |
+
size 766939851
|
checkpoint-66000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-66000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|bos|>",
|
| 4 |
+
"eos_token": "<|eos|>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "TokenizersBackend",
|
| 8 |
+
"unk_token": "<|unk|>"
|
| 9 |
+
}
|