Upload folder using huggingface_hub
Browse files- config.json +57 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForSpeculativeCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoModelForSpeculativeCausalLM": "modeling_speculative_llama.LlamaForSpeculativeCausalLM"
|
10 |
+
},
|
11 |
+
"beagle_add_noise": true,
|
12 |
+
"beagle_attention_offset": "random.randrange(0, 3)",
|
13 |
+
"beagle_attention_wind": "5",
|
14 |
+
"beagle_ckpt_path": null,
|
15 |
+
"beagle_debug": false,
|
16 |
+
"beagle_decoder_key_remap": {},
|
17 |
+
"beagle_dtype": "torch.bfloat16",
|
18 |
+
"beagle_frozen_targets": [],
|
19 |
+
"beagle_git_diff": "",
|
20 |
+
"beagle_git_sha1": "unknown",
|
21 |
+
"beagle_layer_path": "model.layers",
|
22 |
+
"beagle_lmhead_path": "lm_head",
|
23 |
+
"beagle_model_path": "beagle/models/llama2/Llama-2-7b-chat-hf/",
|
24 |
+
"beagle_norm_path": "model.norm",
|
25 |
+
"beagle_output_dir": "output",
|
26 |
+
"beagle_reuse_layer": null,
|
27 |
+
"beagle_rotary_path": "model.rotary_emb",
|
28 |
+
"beagle_run_name": "temp_run",
|
29 |
+
"beagle_seed": 42,
|
30 |
+
"beagle_tokenizer_path": "meta-llama/Llama-2-7b-chat-hf",
|
31 |
+
"beagle_use_fc_eagle": false,
|
32 |
+
"beagle_use_lower_layers": 1,
|
33 |
+
"beagle_use_state_distill": false,
|
34 |
+
"bos_token_id": 1,
|
35 |
+
"eos_token_id": 2,
|
36 |
+
"head_dim": 128,
|
37 |
+
"hidden_act": "silu",
|
38 |
+
"hidden_size": 4096,
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 11008,
|
41 |
+
"max_position_embeddings": 4096,
|
42 |
+
"mlp_bias": false,
|
43 |
+
"model_type": "llama",
|
44 |
+
"num_attention_heads": 32,
|
45 |
+
"num_hidden_layers": 32,
|
46 |
+
"num_key_value_heads": 32,
|
47 |
+
"pretraining_tp": 1,
|
48 |
+
"rms_norm_eps": 1e-05,
|
49 |
+
"rope_scaling": null,
|
50 |
+
"rope_theta": 10000.0,
|
51 |
+
"speculative_base_model": "meta-llama/Llama-2-7b-chat-hf",
|
52 |
+
"tie_word_embeddings": false,
|
53 |
+
"torch_dtype": "bfloat16",
|
54 |
+
"transformers_version": "4.47.1",
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 32000
|
57 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 4096,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"temperature": 0.6,
|
8 |
+
"top_p": 0.9,
|
9 |
+
"transformers_version": "4.47.1"
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73c85b6e8ab75ba047db81e42f4431da5b4567354eb945bfe2573d87304eaf6
|
3 |
+
size 1333832056
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abfd092fbc0b30a9eec9bec2a20d78c8f3eb00ce0eb92ce56f709f1dbe16c935
|
3 |
+
size 809541827
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4c444f7ee3c2b24f101e4b9e5c9de7ceff4b5b362a58f2a73d8c9d6d14377f
|
3 |
+
size 14960
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c79443d180c62f60182990e3c6820eff8399b1f3149d5f3282c010b761549004
|
3 |
+
size 15024
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2015b2a848e043b74a1917ec8d582be3f25f24713cd6da80dec37f74c48d3247
|
3 |
+
size 15024
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f4f57725afd9a7cb7291dbef2cb1e79f096db475e22090579376f5ff60a9e52
|
3 |
+
size 15024
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02e05e4d7bcff55a45308e20fa6c8a00b3f6c98c2173ef58ce3562377b54079b
|
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:a192e7c6547b9965484a15bedfdf49abf3b0f2218076926d004426eb04aaea23
|
3 |
+
size 5368
|