Commit
•
71e7598
1
Parent(s):
de660ce
Upload LlamaForCausalLM
Browse files- config.json +28 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +91 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "fpf-13b-32k/checkpoint-7650",
|
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 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 40,
|
16 |
+
"num_hidden_layers": 9,
|
17 |
+
"num_key_value_heads": 40,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccccbd4f340ed222333754f335376dc861ca20df0f2e07237305959cb865068d
|
3 |
+
size 4978265800
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a42ecce1a4ae0ac137cd0401f8079482571271ed18487ca18cd32cccca20b01
|
3 |
+
size 1386794776
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 6365050880
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
72 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
73 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
74 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
75 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
76 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
81 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
82 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
83 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
84 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
85 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
86 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
87 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
88 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
89 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
90 |
+
}
|
91 |
+
}
|