Uploading folder tiny_LLaMA_1b_8k_cc_merged_v2_8k to hftyzhu/tyzhu/tiny_LLaMA_1b_8k_cc_merged_v2_8kat time 2024-05-18 04:04:31
Browse files
iter-380000-ckpt-step-47500_hf/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 2048,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 5632,
|
| 11 |
+
"max_position_embeddings": 8192,
|
| 12 |
+
"model_type": "llama",
|
| 13 |
+
"num_attention_heads": 32,
|
| 14 |
+
"num_hidden_layers": 22,
|
| 15 |
+
"num_key_value_heads": 4,
|
| 16 |
+
"pretraining_tp": 1,
|
| 17 |
+
"rms_norm_eps": 1e-05,
|
| 18 |
+
"rope_scaling": null,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.31.0.dev0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32000
|
| 24 |
+
}
|
iter-380000-ckpt-step-47500_hf/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ecfeb3c65e7105c2273990d3eddd91d98f4ef3deae8fff3769ac79972d28eb5
|
| 3 |
+
size 4400256000
|