yuanheTian
commited on
Commit
•
2d0d640
1
Parent(s):
7cc4f9a
add file
Browse files- config.json +0 -32
- tokenizer.model +3 -0
config.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/cognitive_comp/ganruyi/Fengshenbang-LM/fengshen/workspace/ziya_llama2_13b_medical/output_exp5/checkpoint-158105",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"bos_token_id": 1,
|
| 8 |
-
"eos_token_id": 2,
|
| 9 |
-
"hidden_act": "silu",
|
| 10 |
-
"hidden_size": 5120,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 13824,
|
| 13 |
-
"layer_norm_eps": 1e-05,
|
| 14 |
-
"max_position_embeddings": 4096,
|
| 15 |
-
"model_type": "llama",
|
| 16 |
-
"num_attention_heads": 40,
|
| 17 |
-
"num_hidden_layers": 40,
|
| 18 |
-
"num_key_value_heads": 40,
|
| 19 |
-
"pad_token_id": 0,
|
| 20 |
-
"pretraining_tp": 1,
|
| 21 |
-
"rms_norm_eps": 1e-06,
|
| 22 |
-
"rope_scaling": null,
|
| 23 |
-
"rope_theta": 10000.0,
|
| 24 |
-
"rotary_emb_base": 10000,
|
| 25 |
-
"rotary_pct": 1,
|
| 26 |
-
"tie_word_embeddings": false,
|
| 27 |
-
"torch_dtype": "bfloat16",
|
| 28 |
-
"transformers_version": "4.34.0.dev0",
|
| 29 |
-
"use_cache": false,
|
| 30 |
-
"use_parallel_residual": false,
|
| 31 |
-
"vocab_size": 39424
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fd7e445833dd0889206aba242c2a51ecbae2437fd328d1759a35475fd8c0423
|
| 3 |
+
size 588619
|