Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,36 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
---
|
| 5 |
+
"_name_or_path": "/data/yyh/model/models--meta-llama--Llama-2-7b-hf",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"LlamaForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_bias": false,
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 1,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 4096,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 11008,
|
| 17 |
+
"max_position_embeddings": 65536,
|
| 18 |
+
"model_type": "llama",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 32,
|
| 21 |
+
"num_key_value_heads": 32,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": {
|
| 26 |
+
"factor": 16.0,
|
| 27 |
+
"type": "dynamic"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 10000.0,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.39.2",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
|
| 36 |
+
Enlonged context length, trained 400 steps on LLaMa-2-7b
|