Hugging Face's logo

w32zhong
/
beagle-ckpt-25000

Safetensors
llama
Model card Files Community
w32zhong commited on
Commit
7b26d65
•
1 Parent(s): a47ea81

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +31 -0
  2. generation_config.json +11 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state_0.pth +3 -0
  6. rng_state_1.pth +3 -0
  7. rng_state_2.pth +3 -0
  8. rng_state_3.pth +3 -0
  9. scheduler.pt +3 -0
  10. trainer_state.json +0 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
3
+ "architectures": [
4
+ "BeagleLlamaForCausualLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "is_encoder_decoder": true,
16
+ "max_position_embeddings": 4096,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 32,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.45.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "eager",
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 4096,
7
+ "pad_token_id": 0,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.45.1"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb3a99214b3ed3d22ccd2ef91404a90af4ddc43278042cbe646647ea024d6dff
3
+ size 1063282368
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edea8b1fe7926c4d2b7c3e566070e5a8d9734af56ebe921ad59dd27f0d0a3978
3
+ size 809541827
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee66090c0ff4401b35f837c26a06cf2a32edfdba69db8d61e3845e11c40a5d2
3
+ size 15024
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e974974c4c14dd476a2747d36e521be222ec0e998b19253025b039b07822b2b
3
+ size 15024
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3448c33da6bd4af16daf122271fe21b1c0e4ab50846d961053c571b8e936f0fa
3
+ size 15024
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc72d1cae2c2694300b19e3e6910d63a396ecf8de4e64d99b3203e5df9d64a2
3
+ size 15024
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fff0805665e820c01768b2fec0aeeb8b82985ea0ca6d6006f8d7993040ccfd34
3
+ size 1064
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7c919010d62bb64209dcca8dc28e6d848d439783d6bbfea95dd8a164d17b2b
3
+ size 5176