Upload folder using huggingface_hub
Browse files- README.md +43 -0
- config.json +29 -0
- mergekit_config.yml +23 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +39 -0
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- psmathur/orca_mini_v3_13b
|
8 |
+
- garage-bAInd/Platypus2-13B
|
9 |
+
- WizardLM/WizardMath-13B-V1.0
|
10 |
+
---
|
11 |
+
|
12 |
+
# psmathur/orca_mini_v3_13b
|
13 |
+
|
14 |
+
psmathur/orca_mini_v3_13b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
15 |
+
* [psmathur/orca_mini_v3_13b](https://huggingface.co/psmathur/orca_mini_v3_13b)
|
16 |
+
* [garage-bAInd/Platypus2-13B](https://huggingface.co/garage-bAInd/Platypus2-13B)
|
17 |
+
* [WizardLM/WizardMath-13B-V1.0](https://huggingface.co/WizardLM/WizardMath-13B-V1.0)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
models:
|
23 |
+
- model: psmathur/orca_mini_v3_13b
|
24 |
+
parameters:
|
25 |
+
density: [1, 0.7, 0.1] # density gradient
|
26 |
+
weight: 1.0
|
27 |
+
- model: garage-bAInd/Platypus2-13B
|
28 |
+
parameters:
|
29 |
+
density: 0.5
|
30 |
+
weight: [0, 0.3, 0.7, 1] # weight gradient
|
31 |
+
- model: WizardLM/WizardMath-13B-V1.0
|
32 |
+
parameters:
|
33 |
+
density: 0.33
|
34 |
+
weight:
|
35 |
+
- filter: mlp
|
36 |
+
value: 0.5
|
37 |
+
- value: 0
|
38 |
+
merge_method: ties
|
39 |
+
base_model: TheBloke/Llama-2-13B-fp16
|
40 |
+
parameters:
|
41 |
+
normalize: true
|
42 |
+
int8_mask: true
|
43 |
+
dtype: float16```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TheBloke/Llama-2-13B-fp16",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 13824,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 40,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.38.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: psmathur/orca_mini_v3_13b
|
4 |
+
parameters:
|
5 |
+
density: [1, 0.7, 0.1] # density gradient
|
6 |
+
weight: 1.0
|
7 |
+
- model: garage-bAInd/Platypus2-13B
|
8 |
+
parameters:
|
9 |
+
density: 0.5
|
10 |
+
weight: [0, 0.3, 0.7, 1] # weight gradient
|
11 |
+
- model: WizardLM/WizardMath-13B-V1.0
|
12 |
+
parameters:
|
13 |
+
density: 0.33
|
14 |
+
weight:
|
15 |
+
- filter: mlp
|
16 |
+
value: 0.5
|
17 |
+
- value: 0
|
18 |
+
merge_method: ties
|
19 |
+
base_model: TheBloke/Llama-2-13B-fp16
|
20 |
+
parameters:
|
21 |
+
normalize: true
|
22 |
+
int8_mask: true
|
23 |
+
dtype: float16
|
model-00001-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1614a24708884629a3c099b5f83e139569a08465db212d3f55f4b134d72d9568
|
3 |
+
size 1955648560
|
model-00002-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3ba531a4dbeb3a0becf690d5390fe225f0e6ae1f2e07bd4f70a388a6e0c9018
|
3 |
+
size 1955658904
|
model-00003-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37d382efbcfed63206c9a6ae9575a8b55920c15517d4a2f1ef8e7d1570a3baa3
|
3 |
+
size 1947784000
|
model-00004-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2e21335d7cb26660d91886cf024513f4cbcfffbd400fff79508f058b932f7f6
|
3 |
+
size 1903230016
|
model-00005-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ff6cac06f216daea20adfeee0356ada16fa1775bb0aaedb96f2459d283945d0
|
3 |
+
size 1903229992
|
model-00006-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a4736c903a4d43426cba8fa590328eda5d048c5b2fa5c1dfcc4d0dff48bbf20
|
3 |
+
size 1976640456
|
model-00007-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caaa8e28f2980e231f1b5ee57b5e409e7c696239561367f00bb2826ab3b0219a
|
3 |
+
size 1955658936
|
model-00008-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ae951aa911a1b10391ba88805631a29cbc225840d896a8ddd78f87c76148a08
|
3 |
+
size 1955648568
|
model-00009-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89cadbd40a66f0b9af66f50036aae110d5826d8fbed96c6c384ff9eb5b40f97b
|
3 |
+
size 1903230016
|
model-00010-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:770575d206d69257a7bc1e5edcd667bc2a363ce5d0e4b622705da40bbb6c47aa
|
3 |
+
size 1903230016
|
model-00011-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef0c8e13bcb852998c108f70f60fe03b35bf8f591092019bb53172ecac28bf01
|
3 |
+
size 1955648568
|
model-00012-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f25c17688429994b8f832487e0e8d4085c7963e572f2573b081eb98c70a2fb70
|
3 |
+
size 1955658936
|
model-00013-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d48c04a765a9cce19d1c6cfbede24cb51e206c3e8180436e6939d95ffbbf9864
|
3 |
+
size 1984515088
|
model-00014-of-00014.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fbe2f646257eeb4f000602636a197755bdf500a3ef704db1312ffbef7a56cd0
|
3 |
+
size 775988592
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.embed_tokens.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "lm_head.weight": "model-00013-of-00014.safetensors", "model.norm.weight": "model-00013-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": null,
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"tokenizer_class": "LlamaTokenizer",
|
37 |
+
"unk_token": "<unk>",
|
38 |
+
"use_default_system_prompt": false
|
39 |
+
}
|