f0419f208c14cc8cae68cc51e0b3b284fdb92a8b1c122ec64bf01508f2506c30
Browse files- .ipynb_checkpoints/README-checkpoint.md +68 -0
- .ipynb_checkpoints/config-checkpoint.json +29 -0
- .ipynb_checkpoints/generation_config-checkpoint.json +8 -0
- .ipynb_checkpoints/model.safetensors.index-checkpoint.json +730 -0
- .ipynb_checkpoints/special_tokens_map-checkpoint.json +24 -0
- .ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +40 -0
- README.md +7 -12
- config.json +2 -1
- generation_config.json +1 -1
- model-00061-of-00061.safetensors +1 -1
- model.safetensors.index.json +1 -321
- special_tokens_map.json +21 -8
- tokenizer_config.json +2 -10
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- shining-valiant
|
7 |
+
- valiant
|
8 |
+
- valiant-labs
|
9 |
+
- llama
|
10 |
+
- llama-2
|
11 |
+
- llama-2-chat
|
12 |
+
- 70b
|
13 |
+
model_type: llama
|
14 |
+
license: llama2
|
15 |
+
---
|
16 |
+
|
17 |
+
|
18 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/5rUJPhu_6LyDvSQogSVhk.jpeg)
|
19 |
+
|
20 |
+
|
21 |
+
Shining Valiant is a chat model built on the Llama 2 architecture, finetuned on our data for insight, creativity, passion, and friendliness.
|
22 |
+
- Uses the llama-2-70b-chat model, with safetensors
|
23 |
+
- Finetuned on multiple runs across private and public data
|
24 |
+
- Data focused on knowledge, enthusiasm, and structured reasoning
|
25 |
+
- **Our new release features greatly expanded personality capability**, bringing a more immersive chat experience
|
26 |
+
|
27 |
+
## Version
|
28 |
+
|
29 |
+
The current version is **1.4!** We've greatly expanded our personality dataset and fixed some bugs to deliver our strongest real-chat experience so far.
|
30 |
+
|
31 |
+
(We're also exploring **new models and architectures**, to deliver helpful open source capabilities for users and creators!)
|
32 |
+
|
33 |
+
Previous versions remain available in the repository. New models will be released for everyone once our team's training and validation process is complete.
|
34 |
+
|
35 |
+
## Evaluation
|
36 |
+
|
37 |
+
Version 1.4 is awaiting results from the Open LLM leaderboard.
|
38 |
+
|
39 |
+
## Prompting Guide
|
40 |
+
Shining Valiant uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts!
|
41 |
+
A few examples of different formats:
|
42 |
+
|
43 |
+
1. [INST] Good morning! Can you let me know how to parse a text file and turn the semicolons into commas? [/INST]
|
44 |
+
|
45 |
+
2. [INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST]
|
46 |
+
|
47 |
+
3. [INST] << SYS >>You are an intelligent, helpful AI assistant.<< /SYS >>Deep dive about a country with interesting history: [/INST]
|
48 |
+
|
49 |
+
## The Model
|
50 |
+
Shining Valiant is built on top of Spell Blade, which uses Llama 2's 70b parameter architecture and features upgraded general and chat capability.
|
51 |
+
|
52 |
+
Our private data focuses primarily on applying Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!
|
53 |
+
|
54 |
+
With this release, the personality component of our Shining Valiant dataset has been greatly improved. We're excited to use it in future releases of this model and others.
|
55 |
+
|
56 |
+
|
57 |
+
|
58 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
|
59 |
+
|
60 |
+
|
61 |
+
Shining Valiant is created by [Valiant Labs.](http://valiantlabs.ca/)
|
62 |
+
|
63 |
+
[Follow us on X for updates on our models!](https://twitter.com/valiant_labs)
|
64 |
+
|
65 |
+
We care about open source.
|
66 |
+
For everyone to use.
|
67 |
+
|
68 |
+
We encourage others to finetune further from our models.
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ValiantLabs/ShiningValiant",
|
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": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_hidden_layers": 80,
|
18 |
+
"num_key_value_heads": 8,
|
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": "float32",
|
26 |
+
"transformers_version": "4.36.2",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
.ipynb_checkpoints/generation_config-checkpoint.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.36.2",
|
7 |
+
"use_cache": false
|
8 |
+
}
|
.ipynb_checkpoints/model.safetensors.index-checkpoint.json
ADDED
@@ -0,0 +1,730 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 275906592768
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00061-of-00061.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00061.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00061.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00061.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00061.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00061.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00061.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00061.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00061.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00061.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00061.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00061.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00061.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00061.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00061.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00061.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00061.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00061.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00061.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00061.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00009-of-00061.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00009-of-00061.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00008-of-00061.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00009-of-00061.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00009-of-00061.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00008-of-00061.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00008-of-00061.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00008-of-00061.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00008-of-00061.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00010-of-00061.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00010-of-00061.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00009-of-00061.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00009-of-00061.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00010-of-00061.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00009-of-00061.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00009-of-00061.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00009-of-00061.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00009-of-00061.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00010-of-00061.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00010-of-00061.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00010-of-00061.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00010-of-00061.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00010-of-00061.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00010-of-00061.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00010-of-00061.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00010-of-00061.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00010-of-00061.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00011-of-00061.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00011-of-00061.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00011-of-00061.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00011-of-00061.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00011-of-00061.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00010-of-00061.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00010-of-00061.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00010-of-00061.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00010-of-00061.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00012-of-00061.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00012-of-00061.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00011-of-00061.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00012-of-00061.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00012-of-00061.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00011-of-00061.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00011-of-00061.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00011-of-00061.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00011-of-00061.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00013-of-00061.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00013-of-00061.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00012-of-00061.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00012-of-00061.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00013-of-00061.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00012-of-00061.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00012-of-00061.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00012-of-00061.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00012-of-00061.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00013-of-00061.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00013-of-00061.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00013-of-00061.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00013-of-00061.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00013-of-00061.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00013-of-00061.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00013-of-00061.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00013-of-00061.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00013-of-00061.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00014-of-00061.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00014-of-00061.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00014-of-00061.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00014-of-00061.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00014-of-00061.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00013-of-00061.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00013-of-00061.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00013-of-00061.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00013-of-00061.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00015-of-00061.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00015-of-00061.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00014-of-00061.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00015-of-00061.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00015-of-00061.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00014-of-00061.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00014-of-00061.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00014-of-00061.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00014-of-00061.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00016-of-00061.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00016-of-00061.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00015-of-00061.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00015-of-00061.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00016-of-00061.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00015-of-00061.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00015-of-00061.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00015-of-00061.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00015-of-00061.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00003-of-00061.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00061.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00061.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00061.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00061.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00061.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00061.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00061.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00061.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00016-of-00061.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00016-of-00061.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00016-of-00061.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00016-of-00061.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00016-of-00061.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00016-of-00061.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00016-of-00061.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00016-of-00061.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00016-of-00061.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00017-of-00061.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00017-of-00061.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00017-of-00061.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00017-of-00061.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00017-of-00061.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00016-of-00061.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00016-of-00061.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00016-of-00061.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00016-of-00061.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00018-of-00061.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00018-of-00061.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00017-of-00061.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00018-of-00061.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00018-of-00061.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00017-of-00061.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00017-of-00061.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00017-of-00061.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00017-of-00061.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00019-of-00061.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00019-of-00061.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00018-of-00061.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00018-of-00061.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00019-of-00061.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00018-of-00061.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00018-of-00061.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00018-of-00061.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00018-of-00061.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00019-of-00061.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00019-of-00061.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00019-of-00061.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00019-of-00061.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00019-of-00061.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00019-of-00061.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00019-of-00061.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00019-of-00061.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00019-of-00061.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00020-of-00061.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00020-of-00061.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00020-of-00061.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00020-of-00061.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00020-of-00061.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00019-of-00061.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00019-of-00061.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00019-of-00061.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00019-of-00061.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00021-of-00061.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00021-of-00061.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00020-of-00061.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00021-of-00061.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00021-of-00061.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00020-of-00061.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00020-of-00061.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00020-of-00061.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00020-of-00061.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00022-of-00061.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00022-of-00061.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00021-of-00061.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00021-of-00061.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00022-of-00061.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00021-of-00061.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00021-of-00061.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00021-of-00061.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00021-of-00061.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00022-of-00061.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00022-of-00061.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00022-of-00061.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00022-of-00061.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00022-of-00061.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00022-of-00061.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00022-of-00061.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00022-of-00061.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00022-of-00061.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00023-of-00061.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00023-of-00061.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00023-of-00061.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00023-of-00061.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00023-of-00061.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00022-of-00061.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00022-of-00061.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00022-of-00061.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00022-of-00061.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00004-of-00061.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00061.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00061.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00061.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00061.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00061.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00061.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00061.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00061.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00024-of-00061.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00024-of-00061.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00023-of-00061.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00024-of-00061.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00024-of-00061.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00023-of-00061.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00023-of-00061.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00023-of-00061.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00023-of-00061.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00025-of-00061.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00025-of-00061.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00024-of-00061.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00024-of-00061.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00025-of-00061.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00024-of-00061.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00024-of-00061.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00024-of-00061.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00024-of-00061.safetensors",
|
242 |
+
"model.layers.32.input_layernorm.weight": "model-00025-of-00061.safetensors",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "model-00025-of-00061.safetensors",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00025-of-00061.safetensors",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "model-00025-of-00061.safetensors",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00025-of-00061.safetensors",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00025-of-00061.safetensors",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00025-of-00061.safetensors",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00025-of-00061.safetensors",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00025-of-00061.safetensors",
|
251 |
+
"model.layers.33.input_layernorm.weight": "model-00026-of-00061.safetensors",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "model-00026-of-00061.safetensors",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00026-of-00061.safetensors",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "model-00026-of-00061.safetensors",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00026-of-00061.safetensors",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00025-of-00061.safetensors",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00025-of-00061.safetensors",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00025-of-00061.safetensors",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00025-of-00061.safetensors",
|
260 |
+
"model.layers.34.input_layernorm.weight": "model-00027-of-00061.safetensors",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "model-00027-of-00061.safetensors",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00026-of-00061.safetensors",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "model-00027-of-00061.safetensors",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00027-of-00061.safetensors",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00026-of-00061.safetensors",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00026-of-00061.safetensors",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00026-of-00061.safetensors",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00026-of-00061.safetensors",
|
269 |
+
"model.layers.35.input_layernorm.weight": "model-00028-of-00061.safetensors",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "model-00028-of-00061.safetensors",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00027-of-00061.safetensors",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "model-00027-of-00061.safetensors",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00028-of-00061.safetensors",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00027-of-00061.safetensors",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00027-of-00061.safetensors",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00027-of-00061.safetensors",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00027-of-00061.safetensors",
|
278 |
+
"model.layers.36.input_layernorm.weight": "model-00028-of-00061.safetensors",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "model-00028-of-00061.safetensors",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00028-of-00061.safetensors",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "model-00028-of-00061.safetensors",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00028-of-00061.safetensors",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00028-of-00061.safetensors",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00028-of-00061.safetensors",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00028-of-00061.safetensors",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00028-of-00061.safetensors",
|
287 |
+
"model.layers.37.input_layernorm.weight": "model-00029-of-00061.safetensors",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "model-00029-of-00061.safetensors",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00029-of-00061.safetensors",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "model-00029-of-00061.safetensors",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00029-of-00061.safetensors",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00028-of-00061.safetensors",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00028-of-00061.safetensors",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00028-of-00061.safetensors",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00028-of-00061.safetensors",
|
296 |
+
"model.layers.38.input_layernorm.weight": "model-00030-of-00061.safetensors",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "model-00030-of-00061.safetensors",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00029-of-00061.safetensors",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "model-00030-of-00061.safetensors",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00030-of-00061.safetensors",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00029-of-00061.safetensors",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00029-of-00061.safetensors",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00029-of-00061.safetensors",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00029-of-00061.safetensors",
|
305 |
+
"model.layers.39.input_layernorm.weight": "model-00031-of-00061.safetensors",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "model-00031-of-00061.safetensors",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00030-of-00061.safetensors",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "model-00030-of-00061.safetensors",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00031-of-00061.safetensors",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00030-of-00061.safetensors",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00030-of-00061.safetensors",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00030-of-00061.safetensors",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00030-of-00061.safetensors",
|
314 |
+
"model.layers.4.input_layernorm.weight": "model-00004-of-00061.safetensors",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00061.safetensors",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00004-of-00061.safetensors",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00061.safetensors",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00061.safetensors",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00061.safetensors",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00061.safetensors",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00004-of-00061.safetensors",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00004-of-00061.safetensors",
|
323 |
+
"model.layers.40.input_layernorm.weight": "model-00031-of-00061.safetensors",
|
324 |
+
"model.layers.40.mlp.down_proj.weight": "model-00031-of-00061.safetensors",
|
325 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00031-of-00061.safetensors",
|
326 |
+
"model.layers.40.mlp.up_proj.weight": "model-00031-of-00061.safetensors",
|
327 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00031-of-00061.safetensors",
|
328 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00031-of-00061.safetensors",
|
329 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00031-of-00061.safetensors",
|
330 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00031-of-00061.safetensors",
|
331 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00031-of-00061.safetensors",
|
332 |
+
"model.layers.41.input_layernorm.weight": "model-00032-of-00061.safetensors",
|
333 |
+
"model.layers.41.mlp.down_proj.weight": "model-00032-of-00061.safetensors",
|
334 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00032-of-00061.safetensors",
|
335 |
+
"model.layers.41.mlp.up_proj.weight": "model-00032-of-00061.safetensors",
|
336 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00032-of-00061.safetensors",
|
337 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00031-of-00061.safetensors",
|
338 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00031-of-00061.safetensors",
|
339 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00031-of-00061.safetensors",
|
340 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00031-of-00061.safetensors",
|
341 |
+
"model.layers.42.input_layernorm.weight": "model-00033-of-00061.safetensors",
|
342 |
+
"model.layers.42.mlp.down_proj.weight": "model-00033-of-00061.safetensors",
|
343 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00032-of-00061.safetensors",
|
344 |
+
"model.layers.42.mlp.up_proj.weight": "model-00033-of-00061.safetensors",
|
345 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00033-of-00061.safetensors",
|
346 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00032-of-00061.safetensors",
|
347 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00032-of-00061.safetensors",
|
348 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00032-of-00061.safetensors",
|
349 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00032-of-00061.safetensors",
|
350 |
+
"model.layers.43.input_layernorm.weight": "model-00034-of-00061.safetensors",
|
351 |
+
"model.layers.43.mlp.down_proj.weight": "model-00034-of-00061.safetensors",
|
352 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00033-of-00061.safetensors",
|
353 |
+
"model.layers.43.mlp.up_proj.weight": "model-00033-of-00061.safetensors",
|
354 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00034-of-00061.safetensors",
|
355 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00033-of-00061.safetensors",
|
356 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00033-of-00061.safetensors",
|
357 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00033-of-00061.safetensors",
|
358 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00033-of-00061.safetensors",
|
359 |
+
"model.layers.44.input_layernorm.weight": "model-00034-of-00061.safetensors",
|
360 |
+
"model.layers.44.mlp.down_proj.weight": "model-00034-of-00061.safetensors",
|
361 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00034-of-00061.safetensors",
|
362 |
+
"model.layers.44.mlp.up_proj.weight": "model-00034-of-00061.safetensors",
|
363 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00034-of-00061.safetensors",
|
364 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00034-of-00061.safetensors",
|
365 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00034-of-00061.safetensors",
|
366 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00034-of-00061.safetensors",
|
367 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00034-of-00061.safetensors",
|
368 |
+
"model.layers.45.input_layernorm.weight": "model-00035-of-00061.safetensors",
|
369 |
+
"model.layers.45.mlp.down_proj.weight": "model-00035-of-00061.safetensors",
|
370 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00035-of-00061.safetensors",
|
371 |
+
"model.layers.45.mlp.up_proj.weight": "model-00035-of-00061.safetensors",
|
372 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00035-of-00061.safetensors",
|
373 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00034-of-00061.safetensors",
|
374 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00034-of-00061.safetensors",
|
375 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00034-of-00061.safetensors",
|
376 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00034-of-00061.safetensors",
|
377 |
+
"model.layers.46.input_layernorm.weight": "model-00036-of-00061.safetensors",
|
378 |
+
"model.layers.46.mlp.down_proj.weight": "model-00036-of-00061.safetensors",
|
379 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00035-of-00061.safetensors",
|
380 |
+
"model.layers.46.mlp.up_proj.weight": "model-00036-of-00061.safetensors",
|
381 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00036-of-00061.safetensors",
|
382 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00035-of-00061.safetensors",
|
383 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00035-of-00061.safetensors",
|
384 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00035-of-00061.safetensors",
|
385 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00035-of-00061.safetensors",
|
386 |
+
"model.layers.47.input_layernorm.weight": "model-00037-of-00061.safetensors",
|
387 |
+
"model.layers.47.mlp.down_proj.weight": "model-00037-of-00061.safetensors",
|
388 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00036-of-00061.safetensors",
|
389 |
+
"model.layers.47.mlp.up_proj.weight": "model-00036-of-00061.safetensors",
|
390 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00037-of-00061.safetensors",
|
391 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00036-of-00061.safetensors",
|
392 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00036-of-00061.safetensors",
|
393 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00036-of-00061.safetensors",
|
394 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00036-of-00061.safetensors",
|
395 |
+
"model.layers.48.input_layernorm.weight": "model-00037-of-00061.safetensors",
|
396 |
+
"model.layers.48.mlp.down_proj.weight": "model-00037-of-00061.safetensors",
|
397 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00037-of-00061.safetensors",
|
398 |
+
"model.layers.48.mlp.up_proj.weight": "model-00037-of-00061.safetensors",
|
399 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00037-of-00061.safetensors",
|
400 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00037-of-00061.safetensors",
|
401 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00037-of-00061.safetensors",
|
402 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00037-of-00061.safetensors",
|
403 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00037-of-00061.safetensors",
|
404 |
+
"model.layers.49.input_layernorm.weight": "model-00038-of-00061.safetensors",
|
405 |
+
"model.layers.49.mlp.down_proj.weight": "model-00038-of-00061.safetensors",
|
406 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00038-of-00061.safetensors",
|
407 |
+
"model.layers.49.mlp.up_proj.weight": "model-00038-of-00061.safetensors",
|
408 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00038-of-00061.safetensors",
|
409 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00037-of-00061.safetensors",
|
410 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00037-of-00061.safetensors",
|
411 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00037-of-00061.safetensors",
|
412 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00037-of-00061.safetensors",
|
413 |
+
"model.layers.5.input_layernorm.weight": "model-00005-of-00061.safetensors",
|
414 |
+
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00061.safetensors",
|
415 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00061.safetensors",
|
416 |
+
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00061.safetensors",
|
417 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00061.safetensors",
|
418 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00061.safetensors",
|
419 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00061.safetensors",
|
420 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00061.safetensors",
|
421 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00061.safetensors",
|
422 |
+
"model.layers.50.input_layernorm.weight": "model-00039-of-00061.safetensors",
|
423 |
+
"model.layers.50.mlp.down_proj.weight": "model-00039-of-00061.safetensors",
|
424 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00038-of-00061.safetensors",
|
425 |
+
"model.layers.50.mlp.up_proj.weight": "model-00039-of-00061.safetensors",
|
426 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00039-of-00061.safetensors",
|
427 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00038-of-00061.safetensors",
|
428 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00038-of-00061.safetensors",
|
429 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00038-of-00061.safetensors",
|
430 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00038-of-00061.safetensors",
|
431 |
+
"model.layers.51.input_layernorm.weight": "model-00040-of-00061.safetensors",
|
432 |
+
"model.layers.51.mlp.down_proj.weight": "model-00040-of-00061.safetensors",
|
433 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00039-of-00061.safetensors",
|
434 |
+
"model.layers.51.mlp.up_proj.weight": "model-00039-of-00061.safetensors",
|
435 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00040-of-00061.safetensors",
|
436 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00039-of-00061.safetensors",
|
437 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00039-of-00061.safetensors",
|
438 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00039-of-00061.safetensors",
|
439 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00039-of-00061.safetensors",
|
440 |
+
"model.layers.52.input_layernorm.weight": "model-00040-of-00061.safetensors",
|
441 |
+
"model.layers.52.mlp.down_proj.weight": "model-00040-of-00061.safetensors",
|
442 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00040-of-00061.safetensors",
|
443 |
+
"model.layers.52.mlp.up_proj.weight": "model-00040-of-00061.safetensors",
|
444 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00040-of-00061.safetensors",
|
445 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00040-of-00061.safetensors",
|
446 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00040-of-00061.safetensors",
|
447 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00040-of-00061.safetensors",
|
448 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00040-of-00061.safetensors",
|
449 |
+
"model.layers.53.input_layernorm.weight": "model-00041-of-00061.safetensors",
|
450 |
+
"model.layers.53.mlp.down_proj.weight": "model-00041-of-00061.safetensors",
|
451 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00041-of-00061.safetensors",
|
452 |
+
"model.layers.53.mlp.up_proj.weight": "model-00041-of-00061.safetensors",
|
453 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00041-of-00061.safetensors",
|
454 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00040-of-00061.safetensors",
|
455 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00040-of-00061.safetensors",
|
456 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00040-of-00061.safetensors",
|
457 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00040-of-00061.safetensors",
|
458 |
+
"model.layers.54.input_layernorm.weight": "model-00042-of-00061.safetensors",
|
459 |
+
"model.layers.54.mlp.down_proj.weight": "model-00042-of-00061.safetensors",
|
460 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00041-of-00061.safetensors",
|
461 |
+
"model.layers.54.mlp.up_proj.weight": "model-00042-of-00061.safetensors",
|
462 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00042-of-00061.safetensors",
|
463 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00041-of-00061.safetensors",
|
464 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00041-of-00061.safetensors",
|
465 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00041-of-00061.safetensors",
|
466 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00041-of-00061.safetensors",
|
467 |
+
"model.layers.55.input_layernorm.weight": "model-00043-of-00061.safetensors",
|
468 |
+
"model.layers.55.mlp.down_proj.weight": "model-00043-of-00061.safetensors",
|
469 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00042-of-00061.safetensors",
|
470 |
+
"model.layers.55.mlp.up_proj.weight": "model-00042-of-00061.safetensors",
|
471 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00043-of-00061.safetensors",
|
472 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00042-of-00061.safetensors",
|
473 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00042-of-00061.safetensors",
|
474 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00042-of-00061.safetensors",
|
475 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00042-of-00061.safetensors",
|
476 |
+
"model.layers.56.input_layernorm.weight": "model-00043-of-00061.safetensors",
|
477 |
+
"model.layers.56.mlp.down_proj.weight": "model-00043-of-00061.safetensors",
|
478 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00043-of-00061.safetensors",
|
479 |
+
"model.layers.56.mlp.up_proj.weight": "model-00043-of-00061.safetensors",
|
480 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00043-of-00061.safetensors",
|
481 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00043-of-00061.safetensors",
|
482 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00043-of-00061.safetensors",
|
483 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00043-of-00061.safetensors",
|
484 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00043-of-00061.safetensors",
|
485 |
+
"model.layers.57.input_layernorm.weight": "model-00044-of-00061.safetensors",
|
486 |
+
"model.layers.57.mlp.down_proj.weight": "model-00044-of-00061.safetensors",
|
487 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00044-of-00061.safetensors",
|
488 |
+
"model.layers.57.mlp.up_proj.weight": "model-00044-of-00061.safetensors",
|
489 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00044-of-00061.safetensors",
|
490 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00043-of-00061.safetensors",
|
491 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00043-of-00061.safetensors",
|
492 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00043-of-00061.safetensors",
|
493 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00043-of-00061.safetensors",
|
494 |
+
"model.layers.58.input_layernorm.weight": "model-00045-of-00061.safetensors",
|
495 |
+
"model.layers.58.mlp.down_proj.weight": "model-00045-of-00061.safetensors",
|
496 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00044-of-00061.safetensors",
|
497 |
+
"model.layers.58.mlp.up_proj.weight": "model-00045-of-00061.safetensors",
|
498 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00045-of-00061.safetensors",
|
499 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00044-of-00061.safetensors",
|
500 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00044-of-00061.safetensors",
|
501 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00044-of-00061.safetensors",
|
502 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00044-of-00061.safetensors",
|
503 |
+
"model.layers.59.input_layernorm.weight": "model-00046-of-00061.safetensors",
|
504 |
+
"model.layers.59.mlp.down_proj.weight": "model-00046-of-00061.safetensors",
|
505 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00045-of-00061.safetensors",
|
506 |
+
"model.layers.59.mlp.up_proj.weight": "model-00045-of-00061.safetensors",
|
507 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00046-of-00061.safetensors",
|
508 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00045-of-00061.safetensors",
|
509 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00045-of-00061.safetensors",
|
510 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00045-of-00061.safetensors",
|
511 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00045-of-00061.safetensors",
|
512 |
+
"model.layers.6.input_layernorm.weight": "model-00006-of-00061.safetensors",
|
513 |
+
"model.layers.6.mlp.down_proj.weight": "model-00006-of-00061.safetensors",
|
514 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00061.safetensors",
|
515 |
+
"model.layers.6.mlp.up_proj.weight": "model-00006-of-00061.safetensors",
|
516 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00006-of-00061.safetensors",
|
517 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00061.safetensors",
|
518 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00061.safetensors",
|
519 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00061.safetensors",
|
520 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00061.safetensors",
|
521 |
+
"model.layers.60.input_layernorm.weight": "model-00046-of-00061.safetensors",
|
522 |
+
"model.layers.60.mlp.down_proj.weight": "model-00046-of-00061.safetensors",
|
523 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00046-of-00061.safetensors",
|
524 |
+
"model.layers.60.mlp.up_proj.weight": "model-00046-of-00061.safetensors",
|
525 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00046-of-00061.safetensors",
|
526 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00046-of-00061.safetensors",
|
527 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00046-of-00061.safetensors",
|
528 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00046-of-00061.safetensors",
|
529 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00046-of-00061.safetensors",
|
530 |
+
"model.layers.61.input_layernorm.weight": "model-00047-of-00061.safetensors",
|
531 |
+
"model.layers.61.mlp.down_proj.weight": "model-00047-of-00061.safetensors",
|
532 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00047-of-00061.safetensors",
|
533 |
+
"model.layers.61.mlp.up_proj.weight": "model-00047-of-00061.safetensors",
|
534 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00047-of-00061.safetensors",
|
535 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00046-of-00061.safetensors",
|
536 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00046-of-00061.safetensors",
|
537 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00046-of-00061.safetensors",
|
538 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00046-of-00061.safetensors",
|
539 |
+
"model.layers.62.input_layernorm.weight": "model-00048-of-00061.safetensors",
|
540 |
+
"model.layers.62.mlp.down_proj.weight": "model-00048-of-00061.safetensors",
|
541 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00047-of-00061.safetensors",
|
542 |
+
"model.layers.62.mlp.up_proj.weight": "model-00048-of-00061.safetensors",
|
543 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00048-of-00061.safetensors",
|
544 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00047-of-00061.safetensors",
|
545 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00047-of-00061.safetensors",
|
546 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00047-of-00061.safetensors",
|
547 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00047-of-00061.safetensors",
|
548 |
+
"model.layers.63.input_layernorm.weight": "model-00049-of-00061.safetensors",
|
549 |
+
"model.layers.63.mlp.down_proj.weight": "model-00049-of-00061.safetensors",
|
550 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00048-of-00061.safetensors",
|
551 |
+
"model.layers.63.mlp.up_proj.weight": "model-00048-of-00061.safetensors",
|
552 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00049-of-00061.safetensors",
|
553 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00048-of-00061.safetensors",
|
554 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00048-of-00061.safetensors",
|
555 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00048-of-00061.safetensors",
|
556 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00048-of-00061.safetensors",
|
557 |
+
"model.layers.64.input_layernorm.weight": "model-00049-of-00061.safetensors",
|
558 |
+
"model.layers.64.mlp.down_proj.weight": "model-00049-of-00061.safetensors",
|
559 |
+
"model.layers.64.mlp.gate_proj.weight": "model-00049-of-00061.safetensors",
|
560 |
+
"model.layers.64.mlp.up_proj.weight": "model-00049-of-00061.safetensors",
|
561 |
+
"model.layers.64.post_attention_layernorm.weight": "model-00049-of-00061.safetensors",
|
562 |
+
"model.layers.64.self_attn.k_proj.weight": "model-00049-of-00061.safetensors",
|
563 |
+
"model.layers.64.self_attn.o_proj.weight": "model-00049-of-00061.safetensors",
|
564 |
+
"model.layers.64.self_attn.q_proj.weight": "model-00049-of-00061.safetensors",
|
565 |
+
"model.layers.64.self_attn.v_proj.weight": "model-00049-of-00061.safetensors",
|
566 |
+
"model.layers.65.input_layernorm.weight": "model-00050-of-00061.safetensors",
|
567 |
+
"model.layers.65.mlp.down_proj.weight": "model-00050-of-00061.safetensors",
|
568 |
+
"model.layers.65.mlp.gate_proj.weight": "model-00050-of-00061.safetensors",
|
569 |
+
"model.layers.65.mlp.up_proj.weight": "model-00050-of-00061.safetensors",
|
570 |
+
"model.layers.65.post_attention_layernorm.weight": "model-00050-of-00061.safetensors",
|
571 |
+
"model.layers.65.self_attn.k_proj.weight": "model-00049-of-00061.safetensors",
|
572 |
+
"model.layers.65.self_attn.o_proj.weight": "model-00049-of-00061.safetensors",
|
573 |
+
"model.layers.65.self_attn.q_proj.weight": "model-00049-of-00061.safetensors",
|
574 |
+
"model.layers.65.self_attn.v_proj.weight": "model-00049-of-00061.safetensors",
|
575 |
+
"model.layers.66.input_layernorm.weight": "model-00051-of-00061.safetensors",
|
576 |
+
"model.layers.66.mlp.down_proj.weight": "model-00051-of-00061.safetensors",
|
577 |
+
"model.layers.66.mlp.gate_proj.weight": "model-00050-of-00061.safetensors",
|
578 |
+
"model.layers.66.mlp.up_proj.weight": "model-00051-of-00061.safetensors",
|
579 |
+
"model.layers.66.post_attention_layernorm.weight": "model-00051-of-00061.safetensors",
|
580 |
+
"model.layers.66.self_attn.k_proj.weight": "model-00050-of-00061.safetensors",
|
581 |
+
"model.layers.66.self_attn.o_proj.weight": "model-00050-of-00061.safetensors",
|
582 |
+
"model.layers.66.self_attn.q_proj.weight": "model-00050-of-00061.safetensors",
|
583 |
+
"model.layers.66.self_attn.v_proj.weight": "model-00050-of-00061.safetensors",
|
584 |
+
"model.layers.67.input_layernorm.weight": "model-00052-of-00061.safetensors",
|
585 |
+
"model.layers.67.mlp.down_proj.weight": "model-00052-of-00061.safetensors",
|
586 |
+
"model.layers.67.mlp.gate_proj.weight": "model-00051-of-00061.safetensors",
|
587 |
+
"model.layers.67.mlp.up_proj.weight": "model-00051-of-00061.safetensors",
|
588 |
+
"model.layers.67.post_attention_layernorm.weight": "model-00052-of-00061.safetensors",
|
589 |
+
"model.layers.67.self_attn.k_proj.weight": "model-00051-of-00061.safetensors",
|
590 |
+
"model.layers.67.self_attn.o_proj.weight": "model-00051-of-00061.safetensors",
|
591 |
+
"model.layers.67.self_attn.q_proj.weight": "model-00051-of-00061.safetensors",
|
592 |
+
"model.layers.67.self_attn.v_proj.weight": "model-00051-of-00061.safetensors",
|
593 |
+
"model.layers.68.input_layernorm.weight": "model-00052-of-00061.safetensors",
|
594 |
+
"model.layers.68.mlp.down_proj.weight": "model-00052-of-00061.safetensors",
|
595 |
+
"model.layers.68.mlp.gate_proj.weight": "model-00052-of-00061.safetensors",
|
596 |
+
"model.layers.68.mlp.up_proj.weight": "model-00052-of-00061.safetensors",
|
597 |
+
"model.layers.68.post_attention_layernorm.weight": "model-00052-of-00061.safetensors",
|
598 |
+
"model.layers.68.self_attn.k_proj.weight": "model-00052-of-00061.safetensors",
|
599 |
+
"model.layers.68.self_attn.o_proj.weight": "model-00052-of-00061.safetensors",
|
600 |
+
"model.layers.68.self_attn.q_proj.weight": "model-00052-of-00061.safetensors",
|
601 |
+
"model.layers.68.self_attn.v_proj.weight": "model-00052-of-00061.safetensors",
|
602 |
+
"model.layers.69.input_layernorm.weight": "model-00053-of-00061.safetensors",
|
603 |
+
"model.layers.69.mlp.down_proj.weight": "model-00053-of-00061.safetensors",
|
604 |
+
"model.layers.69.mlp.gate_proj.weight": "model-00053-of-00061.safetensors",
|
605 |
+
"model.layers.69.mlp.up_proj.weight": "model-00053-of-00061.safetensors",
|
606 |
+
"model.layers.69.post_attention_layernorm.weight": "model-00053-of-00061.safetensors",
|
607 |
+
"model.layers.69.self_attn.k_proj.weight": "model-00052-of-00061.safetensors",
|
608 |
+
"model.layers.69.self_attn.o_proj.weight": "model-00052-of-00061.safetensors",
|
609 |
+
"model.layers.69.self_attn.q_proj.weight": "model-00052-of-00061.safetensors",
|
610 |
+
"model.layers.69.self_attn.v_proj.weight": "model-00052-of-00061.safetensors",
|
611 |
+
"model.layers.7.input_layernorm.weight": "model-00007-of-00061.safetensors",
|
612 |
+
"model.layers.7.mlp.down_proj.weight": "model-00007-of-00061.safetensors",
|
613 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00006-of-00061.safetensors",
|
614 |
+
"model.layers.7.mlp.up_proj.weight": "model-00006-of-00061.safetensors",
|
615 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00007-of-00061.safetensors",
|
616 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00006-of-00061.safetensors",
|
617 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00006-of-00061.safetensors",
|
618 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00006-of-00061.safetensors",
|
619 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00006-of-00061.safetensors",
|
620 |
+
"model.layers.70.input_layernorm.weight": "model-00054-of-00061.safetensors",
|
621 |
+
"model.layers.70.mlp.down_proj.weight": "model-00054-of-00061.safetensors",
|
622 |
+
"model.layers.70.mlp.gate_proj.weight": "model-00053-of-00061.safetensors",
|
623 |
+
"model.layers.70.mlp.up_proj.weight": "model-00054-of-00061.safetensors",
|
624 |
+
"model.layers.70.post_attention_layernorm.weight": "model-00054-of-00061.safetensors",
|
625 |
+
"model.layers.70.self_attn.k_proj.weight": "model-00053-of-00061.safetensors",
|
626 |
+
"model.layers.70.self_attn.o_proj.weight": "model-00053-of-00061.safetensors",
|
627 |
+
"model.layers.70.self_attn.q_proj.weight": "model-00053-of-00061.safetensors",
|
628 |
+
"model.layers.70.self_attn.v_proj.weight": "model-00053-of-00061.safetensors",
|
629 |
+
"model.layers.71.input_layernorm.weight": "model-00055-of-00061.safetensors",
|
630 |
+
"model.layers.71.mlp.down_proj.weight": "model-00055-of-00061.safetensors",
|
631 |
+
"model.layers.71.mlp.gate_proj.weight": "model-00054-of-00061.safetensors",
|
632 |
+
"model.layers.71.mlp.up_proj.weight": "model-00054-of-00061.safetensors",
|
633 |
+
"model.layers.71.post_attention_layernorm.weight": "model-00055-of-00061.safetensors",
|
634 |
+
"model.layers.71.self_attn.k_proj.weight": "model-00054-of-00061.safetensors",
|
635 |
+
"model.layers.71.self_attn.o_proj.weight": "model-00054-of-00061.safetensors",
|
636 |
+
"model.layers.71.self_attn.q_proj.weight": "model-00054-of-00061.safetensors",
|
637 |
+
"model.layers.71.self_attn.v_proj.weight": "model-00054-of-00061.safetensors",
|
638 |
+
"model.layers.72.input_layernorm.weight": "model-00055-of-00061.safetensors",
|
639 |
+
"model.layers.72.mlp.down_proj.weight": "model-00055-of-00061.safetensors",
|
640 |
+
"model.layers.72.mlp.gate_proj.weight": "model-00055-of-00061.safetensors",
|
641 |
+
"model.layers.72.mlp.up_proj.weight": "model-00055-of-00061.safetensors",
|
642 |
+
"model.layers.72.post_attention_layernorm.weight": "model-00055-of-00061.safetensors",
|
643 |
+
"model.layers.72.self_attn.k_proj.weight": "model-00055-of-00061.safetensors",
|
644 |
+
"model.layers.72.self_attn.o_proj.weight": "model-00055-of-00061.safetensors",
|
645 |
+
"model.layers.72.self_attn.q_proj.weight": "model-00055-of-00061.safetensors",
|
646 |
+
"model.layers.72.self_attn.v_proj.weight": "model-00055-of-00061.safetensors",
|
647 |
+
"model.layers.73.input_layernorm.weight": "model-00056-of-00061.safetensors",
|
648 |
+
"model.layers.73.mlp.down_proj.weight": "model-00056-of-00061.safetensors",
|
649 |
+
"model.layers.73.mlp.gate_proj.weight": "model-00056-of-00061.safetensors",
|
650 |
+
"model.layers.73.mlp.up_proj.weight": "model-00056-of-00061.safetensors",
|
651 |
+
"model.layers.73.post_attention_layernorm.weight": "model-00056-of-00061.safetensors",
|
652 |
+
"model.layers.73.self_attn.k_proj.weight": "model-00055-of-00061.safetensors",
|
653 |
+
"model.layers.73.self_attn.o_proj.weight": "model-00055-of-00061.safetensors",
|
654 |
+
"model.layers.73.self_attn.q_proj.weight": "model-00055-of-00061.safetensors",
|
655 |
+
"model.layers.73.self_attn.v_proj.weight": "model-00055-of-00061.safetensors",
|
656 |
+
"model.layers.74.input_layernorm.weight": "model-00057-of-00061.safetensors",
|
657 |
+
"model.layers.74.mlp.down_proj.weight": "model-00057-of-00061.safetensors",
|
658 |
+
"model.layers.74.mlp.gate_proj.weight": "model-00056-of-00061.safetensors",
|
659 |
+
"model.layers.74.mlp.up_proj.weight": "model-00057-of-00061.safetensors",
|
660 |
+
"model.layers.74.post_attention_layernorm.weight": "model-00057-of-00061.safetensors",
|
661 |
+
"model.layers.74.self_attn.k_proj.weight": "model-00056-of-00061.safetensors",
|
662 |
+
"model.layers.74.self_attn.o_proj.weight": "model-00056-of-00061.safetensors",
|
663 |
+
"model.layers.74.self_attn.q_proj.weight": "model-00056-of-00061.safetensors",
|
664 |
+
"model.layers.74.self_attn.v_proj.weight": "model-00056-of-00061.safetensors",
|
665 |
+
"model.layers.75.input_layernorm.weight": "model-00058-of-00061.safetensors",
|
666 |
+
"model.layers.75.mlp.down_proj.weight": "model-00058-of-00061.safetensors",
|
667 |
+
"model.layers.75.mlp.gate_proj.weight": "model-00057-of-00061.safetensors",
|
668 |
+
"model.layers.75.mlp.up_proj.weight": "model-00057-of-00061.safetensors",
|
669 |
+
"model.layers.75.post_attention_layernorm.weight": "model-00058-of-00061.safetensors",
|
670 |
+
"model.layers.75.self_attn.k_proj.weight": "model-00057-of-00061.safetensors",
|
671 |
+
"model.layers.75.self_attn.o_proj.weight": "model-00057-of-00061.safetensors",
|
672 |
+
"model.layers.75.self_attn.q_proj.weight": "model-00057-of-00061.safetensors",
|
673 |
+
"model.layers.75.self_attn.v_proj.weight": "model-00057-of-00061.safetensors",
|
674 |
+
"model.layers.76.input_layernorm.weight": "model-00058-of-00061.safetensors",
|
675 |
+
"model.layers.76.mlp.down_proj.weight": "model-00058-of-00061.safetensors",
|
676 |
+
"model.layers.76.mlp.gate_proj.weight": "model-00058-of-00061.safetensors",
|
677 |
+
"model.layers.76.mlp.up_proj.weight": "model-00058-of-00061.safetensors",
|
678 |
+
"model.layers.76.post_attention_layernorm.weight": "model-00058-of-00061.safetensors",
|
679 |
+
"model.layers.76.self_attn.k_proj.weight": "model-00058-of-00061.safetensors",
|
680 |
+
"model.layers.76.self_attn.o_proj.weight": "model-00058-of-00061.safetensors",
|
681 |
+
"model.layers.76.self_attn.q_proj.weight": "model-00058-of-00061.safetensors",
|
682 |
+
"model.layers.76.self_attn.v_proj.weight": "model-00058-of-00061.safetensors",
|
683 |
+
"model.layers.77.input_layernorm.weight": "model-00059-of-00061.safetensors",
|
684 |
+
"model.layers.77.mlp.down_proj.weight": "model-00059-of-00061.safetensors",
|
685 |
+
"model.layers.77.mlp.gate_proj.weight": "model-00059-of-00061.safetensors",
|
686 |
+
"model.layers.77.mlp.up_proj.weight": "model-00059-of-00061.safetensors",
|
687 |
+
"model.layers.77.post_attention_layernorm.weight": "model-00059-of-00061.safetensors",
|
688 |
+
"model.layers.77.self_attn.k_proj.weight": "model-00058-of-00061.safetensors",
|
689 |
+
"model.layers.77.self_attn.o_proj.weight": "model-00058-of-00061.safetensors",
|
690 |
+
"model.layers.77.self_attn.q_proj.weight": "model-00058-of-00061.safetensors",
|
691 |
+
"model.layers.77.self_attn.v_proj.weight": "model-00058-of-00061.safetensors",
|
692 |
+
"model.layers.78.input_layernorm.weight": "model-00060-of-00061.safetensors",
|
693 |
+
"model.layers.78.mlp.down_proj.weight": "model-00060-of-00061.safetensors",
|
694 |
+
"model.layers.78.mlp.gate_proj.weight": "model-00059-of-00061.safetensors",
|
695 |
+
"model.layers.78.mlp.up_proj.weight": "model-00060-of-00061.safetensors",
|
696 |
+
"model.layers.78.post_attention_layernorm.weight": "model-00060-of-00061.safetensors",
|
697 |
+
"model.layers.78.self_attn.k_proj.weight": "model-00059-of-00061.safetensors",
|
698 |
+
"model.layers.78.self_attn.o_proj.weight": "model-00059-of-00061.safetensors",
|
699 |
+
"model.layers.78.self_attn.q_proj.weight": "model-00059-of-00061.safetensors",
|
700 |
+
"model.layers.78.self_attn.v_proj.weight": "model-00059-of-00061.safetensors",
|
701 |
+
"model.layers.79.input_layernorm.weight": "model-00061-of-00061.safetensors",
|
702 |
+
"model.layers.79.mlp.down_proj.weight": "model-00061-of-00061.safetensors",
|
703 |
+
"model.layers.79.mlp.gate_proj.weight": "model-00060-of-00061.safetensors",
|
704 |
+
"model.layers.79.mlp.up_proj.weight": "model-00060-of-00061.safetensors",
|
705 |
+
"model.layers.79.post_attention_layernorm.weight": "model-00061-of-00061.safetensors",
|
706 |
+
"model.layers.79.self_attn.k_proj.weight": "model-00060-of-00061.safetensors",
|
707 |
+
"model.layers.79.self_attn.o_proj.weight": "model-00060-of-00061.safetensors",
|
708 |
+
"model.layers.79.self_attn.q_proj.weight": "model-00060-of-00061.safetensors",
|
709 |
+
"model.layers.79.self_attn.v_proj.weight": "model-00060-of-00061.safetensors",
|
710 |
+
"model.layers.8.input_layernorm.weight": "model-00007-of-00061.safetensors",
|
711 |
+
"model.layers.8.mlp.down_proj.weight": "model-00007-of-00061.safetensors",
|
712 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00007-of-00061.safetensors",
|
713 |
+
"model.layers.8.mlp.up_proj.weight": "model-00007-of-00061.safetensors",
|
714 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00007-of-00061.safetensors",
|
715 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00007-of-00061.safetensors",
|
716 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00007-of-00061.safetensors",
|
717 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00007-of-00061.safetensors",
|
718 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00007-of-00061.safetensors",
|
719 |
+
"model.layers.9.input_layernorm.weight": "model-00008-of-00061.safetensors",
|
720 |
+
"model.layers.9.mlp.down_proj.weight": "model-00008-of-00061.safetensors",
|
721 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00008-of-00061.safetensors",
|
722 |
+
"model.layers.9.mlp.up_proj.weight": "model-00008-of-00061.safetensors",
|
723 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00008-of-00061.safetensors",
|
724 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00007-of-00061.safetensors",
|
725 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00007-of-00061.safetensors",
|
726 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00007-of-00061.safetensors",
|
727 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00007-of-00061.safetensors",
|
728 |
+
"model.norm.weight": "model-00061-of-00061.safetensors"
|
729 |
+
}
|
730 |
+
}
|
.ipynb_checkpoints/special_tokens_map-checkpoint.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
.ipynb_checkpoints/tokenizer-checkpoint.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
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 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": true
|
40 |
+
}
|
README.md
CHANGED
@@ -22,22 +22,19 @@ Shining Valiant is a chat model built on the Llama 2 architecture, finetuned on
|
|
22 |
- Uses the llama-2-70b-chat model, with safetensors
|
23 |
- Finetuned on multiple runs across private and public data
|
24 |
- Data focused on knowledge, enthusiasm, and structured reasoning
|
|
|
25 |
|
26 |
## Version
|
27 |
|
28 |
-
The current version is **1.
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
(We're also exploring new models and architectures!)
|
33 |
|
34 |
Previous versions remain available in the repository. New models will be released for everyone once our team's training and validation process is complete.
|
35 |
|
36 |
## Evaluation
|
37 |
|
38 |
-
|
39 |
-
|-----------------------|--------|-------|-------|--------|-------|-------|-------|
|
40 |
-
| **Shining Valiant 1.3** | 73.78 | 71.33 | 90.96 | 71.21 | 70.29 | 84.21 | 54.66 |
|
41 |
|
42 |
## Prompting Guide
|
43 |
Shining Valiant uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts!
|
@@ -50,13 +47,11 @@ A few examples of different formats:
|
|
50 |
3. [INST] << SYS >>You are an intelligent, helpful AI assistant.<< /SYS >>Deep dive about a country with interesting history: [/INST]
|
51 |
|
52 |
## The Model
|
53 |
-
Shining Valiant is built on top of
|
54 |
-
|
55 |
-
From there, we've created Shining Valiant through multiple finetuning runs on different compositions of our private dataset.
|
56 |
|
57 |
-
Our private data focuses primarily on applying Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!
|
58 |
|
59 |
-
|
60 |
|
61 |
|
62 |
|
|
|
22 |
- Uses the llama-2-70b-chat model, with safetensors
|
23 |
- Finetuned on multiple runs across private and public data
|
24 |
- Data focused on knowledge, enthusiasm, and structured reasoning
|
25 |
+
- **Our new release features greatly expanded personality capability**, bringing a more immersive chat experience
|
26 |
|
27 |
## Version
|
28 |
|
29 |
+
The current version is **1.4!** We've greatly expanded our personality dataset and fixed some bugs to deliver our strongest real-chat experience so far.
|
30 |
|
31 |
+
(We're also exploring **new models and architectures**, to deliver helpful open source capabilities for users and creators!)
|
|
|
|
|
32 |
|
33 |
Previous versions remain available in the repository. New models will be released for everyone once our team's training and validation process is complete.
|
34 |
|
35 |
## Evaluation
|
36 |
|
37 |
+
Version 1.4 is awaiting results from the Open LLM leaderboard.
|
|
|
|
|
38 |
|
39 |
## Prompting Guide
|
40 |
Shining Valiant uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts!
|
|
|
47 |
3. [INST] << SYS >>You are an intelligent, helpful AI assistant.<< /SYS >>Deep dive about a country with interesting history: [/INST]
|
48 |
|
49 |
## The Model
|
50 |
+
Shining Valiant is built on top of Spell Blade, which uses Llama 2's 70b parameter architecture and features upgraded general and chat capability.
|
|
|
|
|
51 |
|
52 |
+
Our private data focuses primarily on applying Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn!
|
53 |
|
54 |
+
With this release, the personality component of our Shining Valiant dataset has been greatly improved. We're excited to use it in future releases of this model and others.
|
55 |
|
56 |
|
57 |
|
config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
|
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
@@ -22,7 +23,7 @@
|
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "float32",
|
25 |
-
"transformers_version": "4.
|
26 |
"use_cache": false,
|
27 |
"vocab_size": 32000
|
28 |
}
|
|
|
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",
|
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.36.2",
|
27 |
"use_cache": false,
|
28 |
"vocab_size": 32000
|
29 |
}
|
generation_config.json
CHANGED
@@ -3,6 +3,6 @@
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
"use_cache": false
|
8 |
}
|
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.36.2",
|
7 |
"use_cache": false
|
8 |
}
|
model-00061-of-00061.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1988198960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c258787badeecfd94315dbef93055566eff4434d4d0572a37345b65f1b61452
|
3 |
size 1988198960
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00061-of-00061.safetensors",
|
@@ -12,11 +12,7 @@
|
|
12 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00061.safetensors",
|
13 |
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00061.safetensors",
|
14 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00061.safetensors",
|
15 |
-
"model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00061.safetensors",
|
16 |
-
"model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00061.safetensors",
|
17 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00061.safetensors",
|
18 |
-
"model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00061.safetensors",
|
19 |
-
"model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00061.safetensors",
|
20 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00061.safetensors",
|
21 |
"model.layers.1.input_layernorm.weight": "model-00002-of-00061.safetensors",
|
22 |
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00061.safetensors",
|
@@ -25,11 +21,7 @@
|
|
25 |
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00061.safetensors",
|
26 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00061.safetensors",
|
27 |
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00061.safetensors",
|
28 |
-
"model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00061.safetensors",
|
29 |
-
"model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00061.safetensors",
|
30 |
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00061.safetensors",
|
31 |
-
"model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00061.safetensors",
|
32 |
-
"model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00061.safetensors",
|
33 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00061.safetensors",
|
34 |
"model.layers.10.input_layernorm.weight": "model-00009-of-00061.safetensors",
|
35 |
"model.layers.10.mlp.down_proj.weight": "model-00009-of-00061.safetensors",
|
@@ -38,11 +30,7 @@
|
|
38 |
"model.layers.10.post_attention_layernorm.weight": "model-00009-of-00061.safetensors",
|
39 |
"model.layers.10.self_attn.k_proj.weight": "model-00008-of-00061.safetensors",
|
40 |
"model.layers.10.self_attn.o_proj.weight": "model-00008-of-00061.safetensors",
|
41 |
-
"model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00061.safetensors",
|
42 |
-
"model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00061.safetensors",
|
43 |
"model.layers.10.self_attn.q_proj.weight": "model-00008-of-00061.safetensors",
|
44 |
-
"model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00061.safetensors",
|
45 |
-
"model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00061.safetensors",
|
46 |
"model.layers.10.self_attn.v_proj.weight": "model-00008-of-00061.safetensors",
|
47 |
"model.layers.11.input_layernorm.weight": "model-00010-of-00061.safetensors",
|
48 |
"model.layers.11.mlp.down_proj.weight": "model-00010-of-00061.safetensors",
|
@@ -51,11 +39,7 @@
|
|
51 |
"model.layers.11.post_attention_layernorm.weight": "model-00010-of-00061.safetensors",
|
52 |
"model.layers.11.self_attn.k_proj.weight": "model-00009-of-00061.safetensors",
|
53 |
"model.layers.11.self_attn.o_proj.weight": "model-00009-of-00061.safetensors",
|
54 |
-
"model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00061.safetensors",
|
55 |
-
"model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00061.safetensors",
|
56 |
"model.layers.11.self_attn.q_proj.weight": "model-00009-of-00061.safetensors",
|
57 |
-
"model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00061.safetensors",
|
58 |
-
"model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00061.safetensors",
|
59 |
"model.layers.11.self_attn.v_proj.weight": "model-00009-of-00061.safetensors",
|
60 |
"model.layers.12.input_layernorm.weight": "model-00010-of-00061.safetensors",
|
61 |
"model.layers.12.mlp.down_proj.weight": "model-00010-of-00061.safetensors",
|
@@ -64,11 +48,7 @@
|
|
64 |
"model.layers.12.post_attention_layernorm.weight": "model-00010-of-00061.safetensors",
|
65 |
"model.layers.12.self_attn.k_proj.weight": "model-00010-of-00061.safetensors",
|
66 |
"model.layers.12.self_attn.o_proj.weight": "model-00010-of-00061.safetensors",
|
67 |
-
"model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00061.safetensors",
|
68 |
-
"model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00061.safetensors",
|
69 |
"model.layers.12.self_attn.q_proj.weight": "model-00010-of-00061.safetensors",
|
70 |
-
"model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00061.safetensors",
|
71 |
-
"model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00061.safetensors",
|
72 |
"model.layers.12.self_attn.v_proj.weight": "model-00010-of-00061.safetensors",
|
73 |
"model.layers.13.input_layernorm.weight": "model-00011-of-00061.safetensors",
|
74 |
"model.layers.13.mlp.down_proj.weight": "model-00011-of-00061.safetensors",
|
@@ -77,11 +57,7 @@
|
|
77 |
"model.layers.13.post_attention_layernorm.weight": "model-00011-of-00061.safetensors",
|
78 |
"model.layers.13.self_attn.k_proj.weight": "model-00010-of-00061.safetensors",
|
79 |
"model.layers.13.self_attn.o_proj.weight": "model-00010-of-00061.safetensors",
|
80 |
-
"model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00061.safetensors",
|
81 |
-
"model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00061.safetensors",
|
82 |
"model.layers.13.self_attn.q_proj.weight": "model-00010-of-00061.safetensors",
|
83 |
-
"model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00061.safetensors",
|
84 |
-
"model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00061.safetensors",
|
85 |
"model.layers.13.self_attn.v_proj.weight": "model-00010-of-00061.safetensors",
|
86 |
"model.layers.14.input_layernorm.weight": "model-00012-of-00061.safetensors",
|
87 |
"model.layers.14.mlp.down_proj.weight": "model-00012-of-00061.safetensors",
|
@@ -90,11 +66,7 @@
|
|
90 |
"model.layers.14.post_attention_layernorm.weight": "model-00012-of-00061.safetensors",
|
91 |
"model.layers.14.self_attn.k_proj.weight": "model-00011-of-00061.safetensors",
|
92 |
"model.layers.14.self_attn.o_proj.weight": "model-00011-of-00061.safetensors",
|
93 |
-
"model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00061.safetensors",
|
94 |
-
"model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00061.safetensors",
|
95 |
"model.layers.14.self_attn.q_proj.weight": "model-00011-of-00061.safetensors",
|
96 |
-
"model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00061.safetensors",
|
97 |
-
"model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00061.safetensors",
|
98 |
"model.layers.14.self_attn.v_proj.weight": "model-00011-of-00061.safetensors",
|
99 |
"model.layers.15.input_layernorm.weight": "model-00013-of-00061.safetensors",
|
100 |
"model.layers.15.mlp.down_proj.weight": "model-00013-of-00061.safetensors",
|
@@ -103,11 +75,7 @@
|
|
103 |
"model.layers.15.post_attention_layernorm.weight": "model-00013-of-00061.safetensors",
|
104 |
"model.layers.15.self_attn.k_proj.weight": "model-00012-of-00061.safetensors",
|
105 |
"model.layers.15.self_attn.o_proj.weight": "model-00012-of-00061.safetensors",
|
106 |
-
"model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00061.safetensors",
|
107 |
-
"model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00061.safetensors",
|
108 |
"model.layers.15.self_attn.q_proj.weight": "model-00012-of-00061.safetensors",
|
109 |
-
"model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00061.safetensors",
|
110 |
-
"model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00061.safetensors",
|
111 |
"model.layers.15.self_attn.v_proj.weight": "model-00012-of-00061.safetensors",
|
112 |
"model.layers.16.input_layernorm.weight": "model-00013-of-00061.safetensors",
|
113 |
"model.layers.16.mlp.down_proj.weight": "model-00013-of-00061.safetensors",
|
@@ -116,11 +84,7 @@
|
|
116 |
"model.layers.16.post_attention_layernorm.weight": "model-00013-of-00061.safetensors",
|
117 |
"model.layers.16.self_attn.k_proj.weight": "model-00013-of-00061.safetensors",
|
118 |
"model.layers.16.self_attn.o_proj.weight": "model-00013-of-00061.safetensors",
|
119 |
-
"model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00061.safetensors",
|
120 |
-
"model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00061.safetensors",
|
121 |
"model.layers.16.self_attn.q_proj.weight": "model-00013-of-00061.safetensors",
|
122 |
-
"model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00061.safetensors",
|
123 |
-
"model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00061.safetensors",
|
124 |
"model.layers.16.self_attn.v_proj.weight": "model-00013-of-00061.safetensors",
|
125 |
"model.layers.17.input_layernorm.weight": "model-00014-of-00061.safetensors",
|
126 |
"model.layers.17.mlp.down_proj.weight": "model-00014-of-00061.safetensors",
|
@@ -129,11 +93,7 @@
|
|
129 |
"model.layers.17.post_attention_layernorm.weight": "model-00014-of-00061.safetensors",
|
130 |
"model.layers.17.self_attn.k_proj.weight": "model-00013-of-00061.safetensors",
|
131 |
"model.layers.17.self_attn.o_proj.weight": "model-00013-of-00061.safetensors",
|
132 |
-
"model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00061.safetensors",
|
133 |
-
"model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00061.safetensors",
|
134 |
"model.layers.17.self_attn.q_proj.weight": "model-00013-of-00061.safetensors",
|
135 |
-
"model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00061.safetensors",
|
136 |
-
"model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00061.safetensors",
|
137 |
"model.layers.17.self_attn.v_proj.weight": "model-00013-of-00061.safetensors",
|
138 |
"model.layers.18.input_layernorm.weight": "model-00015-of-00061.safetensors",
|
139 |
"model.layers.18.mlp.down_proj.weight": "model-00015-of-00061.safetensors",
|
@@ -142,11 +102,7 @@
|
|
142 |
"model.layers.18.post_attention_layernorm.weight": "model-00015-of-00061.safetensors",
|
143 |
"model.layers.18.self_attn.k_proj.weight": "model-00014-of-00061.safetensors",
|
144 |
"model.layers.18.self_attn.o_proj.weight": "model-00014-of-00061.safetensors",
|
145 |
-
"model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00061.safetensors",
|
146 |
-
"model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00061.safetensors",
|
147 |
"model.layers.18.self_attn.q_proj.weight": "model-00014-of-00061.safetensors",
|
148 |
-
"model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00061.safetensors",
|
149 |
-
"model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00061.safetensors",
|
150 |
"model.layers.18.self_attn.v_proj.weight": "model-00014-of-00061.safetensors",
|
151 |
"model.layers.19.input_layernorm.weight": "model-00016-of-00061.safetensors",
|
152 |
"model.layers.19.mlp.down_proj.weight": "model-00016-of-00061.safetensors",
|
@@ -155,11 +111,7 @@
|
|
155 |
"model.layers.19.post_attention_layernorm.weight": "model-00016-of-00061.safetensors",
|
156 |
"model.layers.19.self_attn.k_proj.weight": "model-00015-of-00061.safetensors",
|
157 |
"model.layers.19.self_attn.o_proj.weight": "model-00015-of-00061.safetensors",
|
158 |
-
"model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00061.safetensors",
|
159 |
-
"model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00061.safetensors",
|
160 |
"model.layers.19.self_attn.q_proj.weight": "model-00015-of-00061.safetensors",
|
161 |
-
"model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00061.safetensors",
|
162 |
-
"model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00061.safetensors",
|
163 |
"model.layers.19.self_attn.v_proj.weight": "model-00015-of-00061.safetensors",
|
164 |
"model.layers.2.input_layernorm.weight": "model-00003-of-00061.safetensors",
|
165 |
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00061.safetensors",
|
@@ -168,11 +120,7 @@
|
|
168 |
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00061.safetensors",
|
169 |
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00061.safetensors",
|
170 |
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00061.safetensors",
|
171 |
-
"model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00061.safetensors",
|
172 |
-
"model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00061.safetensors",
|
173 |
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00061.safetensors",
|
174 |
-
"model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00061.safetensors",
|
175 |
-
"model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00061.safetensors",
|
176 |
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00061.safetensors",
|
177 |
"model.layers.20.input_layernorm.weight": "model-00016-of-00061.safetensors",
|
178 |
"model.layers.20.mlp.down_proj.weight": "model-00016-of-00061.safetensors",
|
@@ -181,11 +129,7 @@
|
|
181 |
"model.layers.20.post_attention_layernorm.weight": "model-00016-of-00061.safetensors",
|
182 |
"model.layers.20.self_attn.k_proj.weight": "model-00016-of-00061.safetensors",
|
183 |
"model.layers.20.self_attn.o_proj.weight": "model-00016-of-00061.safetensors",
|
184 |
-
"model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00061.safetensors",
|
185 |
-
"model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00061.safetensors",
|
186 |
"model.layers.20.self_attn.q_proj.weight": "model-00016-of-00061.safetensors",
|
187 |
-
"model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00061.safetensors",
|
188 |
-
"model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00061.safetensors",
|
189 |
"model.layers.20.self_attn.v_proj.weight": "model-00016-of-00061.safetensors",
|
190 |
"model.layers.21.input_layernorm.weight": "model-00017-of-00061.safetensors",
|
191 |
"model.layers.21.mlp.down_proj.weight": "model-00017-of-00061.safetensors",
|
@@ -194,11 +138,7 @@
|
|
194 |
"model.layers.21.post_attention_layernorm.weight": "model-00017-of-00061.safetensors",
|
195 |
"model.layers.21.self_attn.k_proj.weight": "model-00016-of-00061.safetensors",
|
196 |
"model.layers.21.self_attn.o_proj.weight": "model-00016-of-00061.safetensors",
|
197 |
-
"model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00061.safetensors",
|
198 |
-
"model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00061.safetensors",
|
199 |
"model.layers.21.self_attn.q_proj.weight": "model-00016-of-00061.safetensors",
|
200 |
-
"model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00061.safetensors",
|
201 |
-
"model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00061.safetensors",
|
202 |
"model.layers.21.self_attn.v_proj.weight": "model-00016-of-00061.safetensors",
|
203 |
"model.layers.22.input_layernorm.weight": "model-00018-of-00061.safetensors",
|
204 |
"model.layers.22.mlp.down_proj.weight": "model-00018-of-00061.safetensors",
|
@@ -207,11 +147,7 @@
|
|
207 |
"model.layers.22.post_attention_layernorm.weight": "model-00018-of-00061.safetensors",
|
208 |
"model.layers.22.self_attn.k_proj.weight": "model-00017-of-00061.safetensors",
|
209 |
"model.layers.22.self_attn.o_proj.weight": "model-00017-of-00061.safetensors",
|
210 |
-
"model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00061.safetensors",
|
211 |
-
"model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00061.safetensors",
|
212 |
"model.layers.22.self_attn.q_proj.weight": "model-00017-of-00061.safetensors",
|
213 |
-
"model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00061.safetensors",
|
214 |
-
"model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00061.safetensors",
|
215 |
"model.layers.22.self_attn.v_proj.weight": "model-00017-of-00061.safetensors",
|
216 |
"model.layers.23.input_layernorm.weight": "model-00019-of-00061.safetensors",
|
217 |
"model.layers.23.mlp.down_proj.weight": "model-00019-of-00061.safetensors",
|
@@ -220,11 +156,7 @@
|
|
220 |
"model.layers.23.post_attention_layernorm.weight": "model-00019-of-00061.safetensors",
|
221 |
"model.layers.23.self_attn.k_proj.weight": "model-00018-of-00061.safetensors",
|
222 |
"model.layers.23.self_attn.o_proj.weight": "model-00018-of-00061.safetensors",
|
223 |
-
"model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00061.safetensors",
|
224 |
-
"model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00061.safetensors",
|
225 |
"model.layers.23.self_attn.q_proj.weight": "model-00018-of-00061.safetensors",
|
226 |
-
"model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00061.safetensors",
|
227 |
-
"model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00061.safetensors",
|
228 |
"model.layers.23.self_attn.v_proj.weight": "model-00018-of-00061.safetensors",
|
229 |
"model.layers.24.input_layernorm.weight": "model-00019-of-00061.safetensors",
|
230 |
"model.layers.24.mlp.down_proj.weight": "model-00019-of-00061.safetensors",
|
@@ -233,11 +165,7 @@
|
|
233 |
"model.layers.24.post_attention_layernorm.weight": "model-00019-of-00061.safetensors",
|
234 |
"model.layers.24.self_attn.k_proj.weight": "model-00019-of-00061.safetensors",
|
235 |
"model.layers.24.self_attn.o_proj.weight": "model-00019-of-00061.safetensors",
|
236 |
-
"model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00061.safetensors",
|
237 |
-
"model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00061.safetensors",
|
238 |
"model.layers.24.self_attn.q_proj.weight": "model-00019-of-00061.safetensors",
|
239 |
-
"model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00061.safetensors",
|
240 |
-
"model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00061.safetensors",
|
241 |
"model.layers.24.self_attn.v_proj.weight": "model-00019-of-00061.safetensors",
|
242 |
"model.layers.25.input_layernorm.weight": "model-00020-of-00061.safetensors",
|
243 |
"model.layers.25.mlp.down_proj.weight": "model-00020-of-00061.safetensors",
|
@@ -246,11 +174,7 @@
|
|
246 |
"model.layers.25.post_attention_layernorm.weight": "model-00020-of-00061.safetensors",
|
247 |
"model.layers.25.self_attn.k_proj.weight": "model-00019-of-00061.safetensors",
|
248 |
"model.layers.25.self_attn.o_proj.weight": "model-00019-of-00061.safetensors",
|
249 |
-
"model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00061.safetensors",
|
250 |
-
"model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00061.safetensors",
|
251 |
"model.layers.25.self_attn.q_proj.weight": "model-00019-of-00061.safetensors",
|
252 |
-
"model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00061.safetensors",
|
253 |
-
"model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00061.safetensors",
|
254 |
"model.layers.25.self_attn.v_proj.weight": "model-00019-of-00061.safetensors",
|
255 |
"model.layers.26.input_layernorm.weight": "model-00021-of-00061.safetensors",
|
256 |
"model.layers.26.mlp.down_proj.weight": "model-00021-of-00061.safetensors",
|
@@ -259,11 +183,7 @@
|
|
259 |
"model.layers.26.post_attention_layernorm.weight": "model-00021-of-00061.safetensors",
|
260 |
"model.layers.26.self_attn.k_proj.weight": "model-00020-of-00061.safetensors",
|
261 |
"model.layers.26.self_attn.o_proj.weight": "model-00020-of-00061.safetensors",
|
262 |
-
"model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00061.safetensors",
|
263 |
-
"model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00061.safetensors",
|
264 |
"model.layers.26.self_attn.q_proj.weight": "model-00020-of-00061.safetensors",
|
265 |
-
"model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00061.safetensors",
|
266 |
-
"model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00061.safetensors",
|
267 |
"model.layers.26.self_attn.v_proj.weight": "model-00020-of-00061.safetensors",
|
268 |
"model.layers.27.input_layernorm.weight": "model-00022-of-00061.safetensors",
|
269 |
"model.layers.27.mlp.down_proj.weight": "model-00022-of-00061.safetensors",
|
@@ -272,11 +192,7 @@
|
|
272 |
"model.layers.27.post_attention_layernorm.weight": "model-00022-of-00061.safetensors",
|
273 |
"model.layers.27.self_attn.k_proj.weight": "model-00021-of-00061.safetensors",
|
274 |
"model.layers.27.self_attn.o_proj.weight": "model-00021-of-00061.safetensors",
|
275 |
-
"model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00061.safetensors",
|
276 |
-
"model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00061.safetensors",
|
277 |
"model.layers.27.self_attn.q_proj.weight": "model-00021-of-00061.safetensors",
|
278 |
-
"model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00061.safetensors",
|
279 |
-
"model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00061.safetensors",
|
280 |
"model.layers.27.self_attn.v_proj.weight": "model-00021-of-00061.safetensors",
|
281 |
"model.layers.28.input_layernorm.weight": "model-00022-of-00061.safetensors",
|
282 |
"model.layers.28.mlp.down_proj.weight": "model-00022-of-00061.safetensors",
|
@@ -285,11 +201,7 @@
|
|
285 |
"model.layers.28.post_attention_layernorm.weight": "model-00022-of-00061.safetensors",
|
286 |
"model.layers.28.self_attn.k_proj.weight": "model-00022-of-00061.safetensors",
|
287 |
"model.layers.28.self_attn.o_proj.weight": "model-00022-of-00061.safetensors",
|
288 |
-
"model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00061.safetensors",
|
289 |
-
"model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00061.safetensors",
|
290 |
"model.layers.28.self_attn.q_proj.weight": "model-00022-of-00061.safetensors",
|
291 |
-
"model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00061.safetensors",
|
292 |
-
"model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00061.safetensors",
|
293 |
"model.layers.28.self_attn.v_proj.weight": "model-00022-of-00061.safetensors",
|
294 |
"model.layers.29.input_layernorm.weight": "model-00023-of-00061.safetensors",
|
295 |
"model.layers.29.mlp.down_proj.weight": "model-00023-of-00061.safetensors",
|
@@ -298,11 +210,7 @@
|
|
298 |
"model.layers.29.post_attention_layernorm.weight": "model-00023-of-00061.safetensors",
|
299 |
"model.layers.29.self_attn.k_proj.weight": "model-00022-of-00061.safetensors",
|
300 |
"model.layers.29.self_attn.o_proj.weight": "model-00022-of-00061.safetensors",
|
301 |
-
"model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00061.safetensors",
|
302 |
-
"model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00061.safetensors",
|
303 |
"model.layers.29.self_attn.q_proj.weight": "model-00022-of-00061.safetensors",
|
304 |
-
"model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00061.safetensors",
|
305 |
-
"model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00061.safetensors",
|
306 |
"model.layers.29.self_attn.v_proj.weight": "model-00022-of-00061.safetensors",
|
307 |
"model.layers.3.input_layernorm.weight": "model-00004-of-00061.safetensors",
|
308 |
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00061.safetensors",
|
@@ -311,11 +219,7 @@
|
|
311 |
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00061.safetensors",
|
312 |
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00061.safetensors",
|
313 |
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00061.safetensors",
|
314 |
-
"model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00061.safetensors",
|
315 |
-
"model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00061.safetensors",
|
316 |
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00061.safetensors",
|
317 |
-
"model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00061.safetensors",
|
318 |
-
"model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00061.safetensors",
|
319 |
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00061.safetensors",
|
320 |
"model.layers.30.input_layernorm.weight": "model-00024-of-00061.safetensors",
|
321 |
"model.layers.30.mlp.down_proj.weight": "model-00024-of-00061.safetensors",
|
@@ -324,11 +228,7 @@
|
|
324 |
"model.layers.30.post_attention_layernorm.weight": "model-00024-of-00061.safetensors",
|
325 |
"model.layers.30.self_attn.k_proj.weight": "model-00023-of-00061.safetensors",
|
326 |
"model.layers.30.self_attn.o_proj.weight": "model-00023-of-00061.safetensors",
|
327 |
-
"model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00061.safetensors",
|
328 |
-
"model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00061.safetensors",
|
329 |
"model.layers.30.self_attn.q_proj.weight": "model-00023-of-00061.safetensors",
|
330 |
-
"model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00061.safetensors",
|
331 |
-
"model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00061.safetensors",
|
332 |
"model.layers.30.self_attn.v_proj.weight": "model-00023-of-00061.safetensors",
|
333 |
"model.layers.31.input_layernorm.weight": "model-00025-of-00061.safetensors",
|
334 |
"model.layers.31.mlp.down_proj.weight": "model-00025-of-00061.safetensors",
|
@@ -337,11 +237,7 @@
|
|
337 |
"model.layers.31.post_attention_layernorm.weight": "model-00025-of-00061.safetensors",
|
338 |
"model.layers.31.self_attn.k_proj.weight": "model-00024-of-00061.safetensors",
|
339 |
"model.layers.31.self_attn.o_proj.weight": "model-00024-of-00061.safetensors",
|
340 |
-
"model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00061.safetensors",
|
341 |
-
"model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00061.safetensors",
|
342 |
"model.layers.31.self_attn.q_proj.weight": "model-00024-of-00061.safetensors",
|
343 |
-
"model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00061.safetensors",
|
344 |
-
"model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00061.safetensors",
|
345 |
"model.layers.31.self_attn.v_proj.weight": "model-00024-of-00061.safetensors",
|
346 |
"model.layers.32.input_layernorm.weight": "model-00025-of-00061.safetensors",
|
347 |
"model.layers.32.mlp.down_proj.weight": "model-00025-of-00061.safetensors",
|
@@ -350,11 +246,7 @@
|
|
350 |
"model.layers.32.post_attention_layernorm.weight": "model-00025-of-00061.safetensors",
|
351 |
"model.layers.32.self_attn.k_proj.weight": "model-00025-of-00061.safetensors",
|
352 |
"model.layers.32.self_attn.o_proj.weight": "model-00025-of-00061.safetensors",
|
353 |
-
"model.layers.32.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00061.safetensors",
|
354 |
-
"model.layers.32.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00061.safetensors",
|
355 |
"model.layers.32.self_attn.q_proj.weight": "model-00025-of-00061.safetensors",
|
356 |
-
"model.layers.32.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00061.safetensors",
|
357 |
-
"model.layers.32.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00061.safetensors",
|
358 |
"model.layers.32.self_attn.v_proj.weight": "model-00025-of-00061.safetensors",
|
359 |
"model.layers.33.input_layernorm.weight": "model-00026-of-00061.safetensors",
|
360 |
"model.layers.33.mlp.down_proj.weight": "model-00026-of-00061.safetensors",
|
@@ -363,11 +255,7 @@
|
|
363 |
"model.layers.33.post_attention_layernorm.weight": "model-00026-of-00061.safetensors",
|
364 |
"model.layers.33.self_attn.k_proj.weight": "model-00025-of-00061.safetensors",
|
365 |
"model.layers.33.self_attn.o_proj.weight": "model-00025-of-00061.safetensors",
|
366 |
-
"model.layers.33.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00061.safetensors",
|
367 |
-
"model.layers.33.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00061.safetensors",
|
368 |
"model.layers.33.self_attn.q_proj.weight": "model-00025-of-00061.safetensors",
|
369 |
-
"model.layers.33.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00061.safetensors",
|
370 |
-
"model.layers.33.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00061.safetensors",
|
371 |
"model.layers.33.self_attn.v_proj.weight": "model-00025-of-00061.safetensors",
|
372 |
"model.layers.34.input_layernorm.weight": "model-00027-of-00061.safetensors",
|
373 |
"model.layers.34.mlp.down_proj.weight": "model-00027-of-00061.safetensors",
|
@@ -376,11 +264,7 @@
|
|
376 |
"model.layers.34.post_attention_layernorm.weight": "model-00027-of-00061.safetensors",
|
377 |
"model.layers.34.self_attn.k_proj.weight": "model-00026-of-00061.safetensors",
|
378 |
"model.layers.34.self_attn.o_proj.weight": "model-00026-of-00061.safetensors",
|
379 |
-
"model.layers.34.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00061.safetensors",
|
380 |
-
"model.layers.34.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00061.safetensors",
|
381 |
"model.layers.34.self_attn.q_proj.weight": "model-00026-of-00061.safetensors",
|
382 |
-
"model.layers.34.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00061.safetensors",
|
383 |
-
"model.layers.34.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00061.safetensors",
|
384 |
"model.layers.34.self_attn.v_proj.weight": "model-00026-of-00061.safetensors",
|
385 |
"model.layers.35.input_layernorm.weight": "model-00028-of-00061.safetensors",
|
386 |
"model.layers.35.mlp.down_proj.weight": "model-00028-of-00061.safetensors",
|
@@ -389,11 +273,7 @@
|
|
389 |
"model.layers.35.post_attention_layernorm.weight": "model-00028-of-00061.safetensors",
|
390 |
"model.layers.35.self_attn.k_proj.weight": "model-00027-of-00061.safetensors",
|
391 |
"model.layers.35.self_attn.o_proj.weight": "model-00027-of-00061.safetensors",
|
392 |
-
"model.layers.35.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00061.safetensors",
|
393 |
-
"model.layers.35.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00061.safetensors",
|
394 |
"model.layers.35.self_attn.q_proj.weight": "model-00027-of-00061.safetensors",
|
395 |
-
"model.layers.35.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00061.safetensors",
|
396 |
-
"model.layers.35.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00061.safetensors",
|
397 |
"model.layers.35.self_attn.v_proj.weight": "model-00027-of-00061.safetensors",
|
398 |
"model.layers.36.input_layernorm.weight": "model-00028-of-00061.safetensors",
|
399 |
"model.layers.36.mlp.down_proj.weight": "model-00028-of-00061.safetensors",
|
@@ -402,11 +282,7 @@
|
|
402 |
"model.layers.36.post_attention_layernorm.weight": "model-00028-of-00061.safetensors",
|
403 |
"model.layers.36.self_attn.k_proj.weight": "model-00028-of-00061.safetensors",
|
404 |
"model.layers.36.self_attn.o_proj.weight": "model-00028-of-00061.safetensors",
|
405 |
-
"model.layers.36.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00061.safetensors",
|
406 |
-
"model.layers.36.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00061.safetensors",
|
407 |
"model.layers.36.self_attn.q_proj.weight": "model-00028-of-00061.safetensors",
|
408 |
-
"model.layers.36.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00061.safetensors",
|
409 |
-
"model.layers.36.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00061.safetensors",
|
410 |
"model.layers.36.self_attn.v_proj.weight": "model-00028-of-00061.safetensors",
|
411 |
"model.layers.37.input_layernorm.weight": "model-00029-of-00061.safetensors",
|
412 |
"model.layers.37.mlp.down_proj.weight": "model-00029-of-00061.safetensors",
|
@@ -415,11 +291,7 @@
|
|
415 |
"model.layers.37.post_attention_layernorm.weight": "model-00029-of-00061.safetensors",
|
416 |
"model.layers.37.self_attn.k_proj.weight": "model-00028-of-00061.safetensors",
|
417 |
"model.layers.37.self_attn.o_proj.weight": "model-00028-of-00061.safetensors",
|
418 |
-
"model.layers.37.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00061.safetensors",
|
419 |
-
"model.layers.37.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00061.safetensors",
|
420 |
"model.layers.37.self_attn.q_proj.weight": "model-00028-of-00061.safetensors",
|
421 |
-
"model.layers.37.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00061.safetensors",
|
422 |
-
"model.layers.37.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00061.safetensors",
|
423 |
"model.layers.37.self_attn.v_proj.weight": "model-00028-of-00061.safetensors",
|
424 |
"model.layers.38.input_layernorm.weight": "model-00030-of-00061.safetensors",
|
425 |
"model.layers.38.mlp.down_proj.weight": "model-00030-of-00061.safetensors",
|
@@ -428,11 +300,7 @@
|
|
428 |
"model.layers.38.post_attention_layernorm.weight": "model-00030-of-00061.safetensors",
|
429 |
"model.layers.38.self_attn.k_proj.weight": "model-00029-of-00061.safetensors",
|
430 |
"model.layers.38.self_attn.o_proj.weight": "model-00029-of-00061.safetensors",
|
431 |
-
"model.layers.38.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00061.safetensors",
|
432 |
-
"model.layers.38.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00061.safetensors",
|
433 |
"model.layers.38.self_attn.q_proj.weight": "model-00029-of-00061.safetensors",
|
434 |
-
"model.layers.38.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00061.safetensors",
|
435 |
-
"model.layers.38.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00061.safetensors",
|
436 |
"model.layers.38.self_attn.v_proj.weight": "model-00029-of-00061.safetensors",
|
437 |
"model.layers.39.input_layernorm.weight": "model-00031-of-00061.safetensors",
|
438 |
"model.layers.39.mlp.down_proj.weight": "model-00031-of-00061.safetensors",
|
@@ -441,11 +309,7 @@
|
|
441 |
"model.layers.39.post_attention_layernorm.weight": "model-00031-of-00061.safetensors",
|
442 |
"model.layers.39.self_attn.k_proj.weight": "model-00030-of-00061.safetensors",
|
443 |
"model.layers.39.self_attn.o_proj.weight": "model-00030-of-00061.safetensors",
|
444 |
-
"model.layers.39.self_attn.q_proj.lora_A.default.weight": "model-00030-of-00061.safetensors",
|
445 |
-
"model.layers.39.self_attn.q_proj.lora_B.default.weight": "model-00030-of-00061.safetensors",
|
446 |
"model.layers.39.self_attn.q_proj.weight": "model-00030-of-00061.safetensors",
|
447 |
-
"model.layers.39.self_attn.v_proj.lora_A.default.weight": "model-00030-of-00061.safetensors",
|
448 |
-
"model.layers.39.self_attn.v_proj.lora_B.default.weight": "model-00030-of-00061.safetensors",
|
449 |
"model.layers.39.self_attn.v_proj.weight": "model-00030-of-00061.safetensors",
|
450 |
"model.layers.4.input_layernorm.weight": "model-00004-of-00061.safetensors",
|
451 |
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00061.safetensors",
|
@@ -454,11 +318,7 @@
|
|
454 |
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00061.safetensors",
|
455 |
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00061.safetensors",
|
456 |
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00061.safetensors",
|
457 |
-
"model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00061.safetensors",
|
458 |
-
"model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00061.safetensors",
|
459 |
"model.layers.4.self_attn.q_proj.weight": "model-00004-of-00061.safetensors",
|
460 |
-
"model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00061.safetensors",
|
461 |
-
"model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00061.safetensors",
|
462 |
"model.layers.4.self_attn.v_proj.weight": "model-00004-of-00061.safetensors",
|
463 |
"model.layers.40.input_layernorm.weight": "model-00031-of-00061.safetensors",
|
464 |
"model.layers.40.mlp.down_proj.weight": "model-00031-of-00061.safetensors",
|
@@ -467,11 +327,7 @@
|
|
467 |
"model.layers.40.post_attention_layernorm.weight": "model-00031-of-00061.safetensors",
|
468 |
"model.layers.40.self_attn.k_proj.weight": "model-00031-of-00061.safetensors",
|
469 |
"model.layers.40.self_attn.o_proj.weight": "model-00031-of-00061.safetensors",
|
470 |
-
"model.layers.40.self_attn.q_proj.lora_A.default.weight": "model-00031-of-00061.safetensors",
|
471 |
-
"model.layers.40.self_attn.q_proj.lora_B.default.weight": "model-00031-of-00061.safetensors",
|
472 |
"model.layers.40.self_attn.q_proj.weight": "model-00031-of-00061.safetensors",
|
473 |
-
"model.layers.40.self_attn.v_proj.lora_A.default.weight": "model-00031-of-00061.safetensors",
|
474 |
-
"model.layers.40.self_attn.v_proj.lora_B.default.weight": "model-00031-of-00061.safetensors",
|
475 |
"model.layers.40.self_attn.v_proj.weight": "model-00031-of-00061.safetensors",
|
476 |
"model.layers.41.input_layernorm.weight": "model-00032-of-00061.safetensors",
|
477 |
"model.layers.41.mlp.down_proj.weight": "model-00032-of-00061.safetensors",
|
@@ -480,11 +336,7 @@
|
|
480 |
"model.layers.41.post_attention_layernorm.weight": "model-00032-of-00061.safetensors",
|
481 |
"model.layers.41.self_attn.k_proj.weight": "model-00031-of-00061.safetensors",
|
482 |
"model.layers.41.self_attn.o_proj.weight": "model-00031-of-00061.safetensors",
|
483 |
-
"model.layers.41.self_attn.q_proj.lora_A.default.weight": "model-00031-of-00061.safetensors",
|
484 |
-
"model.layers.41.self_attn.q_proj.lora_B.default.weight": "model-00031-of-00061.safetensors",
|
485 |
"model.layers.41.self_attn.q_proj.weight": "model-00031-of-00061.safetensors",
|
486 |
-
"model.layers.41.self_attn.v_proj.lora_A.default.weight": "model-00031-of-00061.safetensors",
|
487 |
-
"model.layers.41.self_attn.v_proj.lora_B.default.weight": "model-00031-of-00061.safetensors",
|
488 |
"model.layers.41.self_attn.v_proj.weight": "model-00031-of-00061.safetensors",
|
489 |
"model.layers.42.input_layernorm.weight": "model-00033-of-00061.safetensors",
|
490 |
"model.layers.42.mlp.down_proj.weight": "model-00033-of-00061.safetensors",
|
@@ -493,11 +345,7 @@
|
|
493 |
"model.layers.42.post_attention_layernorm.weight": "model-00033-of-00061.safetensors",
|
494 |
"model.layers.42.self_attn.k_proj.weight": "model-00032-of-00061.safetensors",
|
495 |
"model.layers.42.self_attn.o_proj.weight": "model-00032-of-00061.safetensors",
|
496 |
-
"model.layers.42.self_attn.q_proj.lora_A.default.weight": "model-00032-of-00061.safetensors",
|
497 |
-
"model.layers.42.self_attn.q_proj.lora_B.default.weight": "model-00032-of-00061.safetensors",
|
498 |
"model.layers.42.self_attn.q_proj.weight": "model-00032-of-00061.safetensors",
|
499 |
-
"model.layers.42.self_attn.v_proj.lora_A.default.weight": "model-00032-of-00061.safetensors",
|
500 |
-
"model.layers.42.self_attn.v_proj.lora_B.default.weight": "model-00032-of-00061.safetensors",
|
501 |
"model.layers.42.self_attn.v_proj.weight": "model-00032-of-00061.safetensors",
|
502 |
"model.layers.43.input_layernorm.weight": "model-00034-of-00061.safetensors",
|
503 |
"model.layers.43.mlp.down_proj.weight": "model-00034-of-00061.safetensors",
|
@@ -506,11 +354,7 @@
|
|
506 |
"model.layers.43.post_attention_layernorm.weight": "model-00034-of-00061.safetensors",
|
507 |
"model.layers.43.self_attn.k_proj.weight": "model-00033-of-00061.safetensors",
|
508 |
"model.layers.43.self_attn.o_proj.weight": "model-00033-of-00061.safetensors",
|
509 |
-
"model.layers.43.self_attn.q_proj.lora_A.default.weight": "model-00033-of-00061.safetensors",
|
510 |
-
"model.layers.43.self_attn.q_proj.lora_B.default.weight": "model-00033-of-00061.safetensors",
|
511 |
"model.layers.43.self_attn.q_proj.weight": "model-00033-of-00061.safetensors",
|
512 |
-
"model.layers.43.self_attn.v_proj.lora_A.default.weight": "model-00033-of-00061.safetensors",
|
513 |
-
"model.layers.43.self_attn.v_proj.lora_B.default.weight": "model-00033-of-00061.safetensors",
|
514 |
"model.layers.43.self_attn.v_proj.weight": "model-00033-of-00061.safetensors",
|
515 |
"model.layers.44.input_layernorm.weight": "model-00034-of-00061.safetensors",
|
516 |
"model.layers.44.mlp.down_proj.weight": "model-00034-of-00061.safetensors",
|
@@ -519,11 +363,7 @@
|
|
519 |
"model.layers.44.post_attention_layernorm.weight": "model-00034-of-00061.safetensors",
|
520 |
"model.layers.44.self_attn.k_proj.weight": "model-00034-of-00061.safetensors",
|
521 |
"model.layers.44.self_attn.o_proj.weight": "model-00034-of-00061.safetensors",
|
522 |
-
"model.layers.44.self_attn.q_proj.lora_A.default.weight": "model-00034-of-00061.safetensors",
|
523 |
-
"model.layers.44.self_attn.q_proj.lora_B.default.weight": "model-00034-of-00061.safetensors",
|
524 |
"model.layers.44.self_attn.q_proj.weight": "model-00034-of-00061.safetensors",
|
525 |
-
"model.layers.44.self_attn.v_proj.lora_A.default.weight": "model-00034-of-00061.safetensors",
|
526 |
-
"model.layers.44.self_attn.v_proj.lora_B.default.weight": "model-00034-of-00061.safetensors",
|
527 |
"model.layers.44.self_attn.v_proj.weight": "model-00034-of-00061.safetensors",
|
528 |
"model.layers.45.input_layernorm.weight": "model-00035-of-00061.safetensors",
|
529 |
"model.layers.45.mlp.down_proj.weight": "model-00035-of-00061.safetensors",
|
@@ -532,11 +372,7 @@
|
|
532 |
"model.layers.45.post_attention_layernorm.weight": "model-00035-of-00061.safetensors",
|
533 |
"model.layers.45.self_attn.k_proj.weight": "model-00034-of-00061.safetensors",
|
534 |
"model.layers.45.self_attn.o_proj.weight": "model-00034-of-00061.safetensors",
|
535 |
-
"model.layers.45.self_attn.q_proj.lora_A.default.weight": "model-00034-of-00061.safetensors",
|
536 |
-
"model.layers.45.self_attn.q_proj.lora_B.default.weight": "model-00034-of-00061.safetensors",
|
537 |
"model.layers.45.self_attn.q_proj.weight": "model-00034-of-00061.safetensors",
|
538 |
-
"model.layers.45.self_attn.v_proj.lora_A.default.weight": "model-00034-of-00061.safetensors",
|
539 |
-
"model.layers.45.self_attn.v_proj.lora_B.default.weight": "model-00034-of-00061.safetensors",
|
540 |
"model.layers.45.self_attn.v_proj.weight": "model-00034-of-00061.safetensors",
|
541 |
"model.layers.46.input_layernorm.weight": "model-00036-of-00061.safetensors",
|
542 |
"model.layers.46.mlp.down_proj.weight": "model-00036-of-00061.safetensors",
|
@@ -545,11 +381,7 @@
|
|
545 |
"model.layers.46.post_attention_layernorm.weight": "model-00036-of-00061.safetensors",
|
546 |
"model.layers.46.self_attn.k_proj.weight": "model-00035-of-00061.safetensors",
|
547 |
"model.layers.46.self_attn.o_proj.weight": "model-00035-of-00061.safetensors",
|
548 |
-
"model.layers.46.self_attn.q_proj.lora_A.default.weight": "model-00035-of-00061.safetensors",
|
549 |
-
"model.layers.46.self_attn.q_proj.lora_B.default.weight": "model-00035-of-00061.safetensors",
|
550 |
"model.layers.46.self_attn.q_proj.weight": "model-00035-of-00061.safetensors",
|
551 |
-
"model.layers.46.self_attn.v_proj.lora_A.default.weight": "model-00035-of-00061.safetensors",
|
552 |
-
"model.layers.46.self_attn.v_proj.lora_B.default.weight": "model-00035-of-00061.safetensors",
|
553 |
"model.layers.46.self_attn.v_proj.weight": "model-00035-of-00061.safetensors",
|
554 |
"model.layers.47.input_layernorm.weight": "model-00037-of-00061.safetensors",
|
555 |
"model.layers.47.mlp.down_proj.weight": "model-00037-of-00061.safetensors",
|
@@ -558,11 +390,7 @@
|
|
558 |
"model.layers.47.post_attention_layernorm.weight": "model-00037-of-00061.safetensors",
|
559 |
"model.layers.47.self_attn.k_proj.weight": "model-00036-of-00061.safetensors",
|
560 |
"model.layers.47.self_attn.o_proj.weight": "model-00036-of-00061.safetensors",
|
561 |
-
"model.layers.47.self_attn.q_proj.lora_A.default.weight": "model-00036-of-00061.safetensors",
|
562 |
-
"model.layers.47.self_attn.q_proj.lora_B.default.weight": "model-00036-of-00061.safetensors",
|
563 |
"model.layers.47.self_attn.q_proj.weight": "model-00036-of-00061.safetensors",
|
564 |
-
"model.layers.47.self_attn.v_proj.lora_A.default.weight": "model-00036-of-00061.safetensors",
|
565 |
-
"model.layers.47.self_attn.v_proj.lora_B.default.weight": "model-00036-of-00061.safetensors",
|
566 |
"model.layers.47.self_attn.v_proj.weight": "model-00036-of-00061.safetensors",
|
567 |
"model.layers.48.input_layernorm.weight": "model-00037-of-00061.safetensors",
|
568 |
"model.layers.48.mlp.down_proj.weight": "model-00037-of-00061.safetensors",
|
@@ -571,11 +399,7 @@
|
|
571 |
"model.layers.48.post_attention_layernorm.weight": "model-00037-of-00061.safetensors",
|
572 |
"model.layers.48.self_attn.k_proj.weight": "model-00037-of-00061.safetensors",
|
573 |
"model.layers.48.self_attn.o_proj.weight": "model-00037-of-00061.safetensors",
|
574 |
-
"model.layers.48.self_attn.q_proj.lora_A.default.weight": "model-00037-of-00061.safetensors",
|
575 |
-
"model.layers.48.self_attn.q_proj.lora_B.default.weight": "model-00037-of-00061.safetensors",
|
576 |
"model.layers.48.self_attn.q_proj.weight": "model-00037-of-00061.safetensors",
|
577 |
-
"model.layers.48.self_attn.v_proj.lora_A.default.weight": "model-00037-of-00061.safetensors",
|
578 |
-
"model.layers.48.self_attn.v_proj.lora_B.default.weight": "model-00037-of-00061.safetensors",
|
579 |
"model.layers.48.self_attn.v_proj.weight": "model-00037-of-00061.safetensors",
|
580 |
"model.layers.49.input_layernorm.weight": "model-00038-of-00061.safetensors",
|
581 |
"model.layers.49.mlp.down_proj.weight": "model-00038-of-00061.safetensors",
|
@@ -584,11 +408,7 @@
|
|
584 |
"model.layers.49.post_attention_layernorm.weight": "model-00038-of-00061.safetensors",
|
585 |
"model.layers.49.self_attn.k_proj.weight": "model-00037-of-00061.safetensors",
|
586 |
"model.layers.49.self_attn.o_proj.weight": "model-00037-of-00061.safetensors",
|
587 |
-
"model.layers.49.self_attn.q_proj.lora_A.default.weight": "model-00037-of-00061.safetensors",
|
588 |
-
"model.layers.49.self_attn.q_proj.lora_B.default.weight": "model-00037-of-00061.safetensors",
|
589 |
"model.layers.49.self_attn.q_proj.weight": "model-00037-of-00061.safetensors",
|
590 |
-
"model.layers.49.self_attn.v_proj.lora_A.default.weight": "model-00037-of-00061.safetensors",
|
591 |
-
"model.layers.49.self_attn.v_proj.lora_B.default.weight": "model-00037-of-00061.safetensors",
|
592 |
"model.layers.49.self_attn.v_proj.weight": "model-00037-of-00061.safetensors",
|
593 |
"model.layers.5.input_layernorm.weight": "model-00005-of-00061.safetensors",
|
594 |
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00061.safetensors",
|
@@ -597,11 +417,7 @@
|
|
597 |
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00061.safetensors",
|
598 |
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00061.safetensors",
|
599 |
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00061.safetensors",
|
600 |
-
"model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00061.safetensors",
|
601 |
-
"model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00061.safetensors",
|
602 |
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00061.safetensors",
|
603 |
-
"model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00061.safetensors",
|
604 |
-
"model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00061.safetensors",
|
605 |
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00061.safetensors",
|
606 |
"model.layers.50.input_layernorm.weight": "model-00039-of-00061.safetensors",
|
607 |
"model.layers.50.mlp.down_proj.weight": "model-00039-of-00061.safetensors",
|
@@ -610,11 +426,7 @@
|
|
610 |
"model.layers.50.post_attention_layernorm.weight": "model-00039-of-00061.safetensors",
|
611 |
"model.layers.50.self_attn.k_proj.weight": "model-00038-of-00061.safetensors",
|
612 |
"model.layers.50.self_attn.o_proj.weight": "model-00038-of-00061.safetensors",
|
613 |
-
"model.layers.50.self_attn.q_proj.lora_A.default.weight": "model-00038-of-00061.safetensors",
|
614 |
-
"model.layers.50.self_attn.q_proj.lora_B.default.weight": "model-00038-of-00061.safetensors",
|
615 |
"model.layers.50.self_attn.q_proj.weight": "model-00038-of-00061.safetensors",
|
616 |
-
"model.layers.50.self_attn.v_proj.lora_A.default.weight": "model-00038-of-00061.safetensors",
|
617 |
-
"model.layers.50.self_attn.v_proj.lora_B.default.weight": "model-00038-of-00061.safetensors",
|
618 |
"model.layers.50.self_attn.v_proj.weight": "model-00038-of-00061.safetensors",
|
619 |
"model.layers.51.input_layernorm.weight": "model-00040-of-00061.safetensors",
|
620 |
"model.layers.51.mlp.down_proj.weight": "model-00040-of-00061.safetensors",
|
@@ -623,11 +435,7 @@
|
|
623 |
"model.layers.51.post_attention_layernorm.weight": "model-00040-of-00061.safetensors",
|
624 |
"model.layers.51.self_attn.k_proj.weight": "model-00039-of-00061.safetensors",
|
625 |
"model.layers.51.self_attn.o_proj.weight": "model-00039-of-00061.safetensors",
|
626 |
-
"model.layers.51.self_attn.q_proj.lora_A.default.weight": "model-00039-of-00061.safetensors",
|
627 |
-
"model.layers.51.self_attn.q_proj.lora_B.default.weight": "model-00039-of-00061.safetensors",
|
628 |
"model.layers.51.self_attn.q_proj.weight": "model-00039-of-00061.safetensors",
|
629 |
-
"model.layers.51.self_attn.v_proj.lora_A.default.weight": "model-00039-of-00061.safetensors",
|
630 |
-
"model.layers.51.self_attn.v_proj.lora_B.default.weight": "model-00039-of-00061.safetensors",
|
631 |
"model.layers.51.self_attn.v_proj.weight": "model-00039-of-00061.safetensors",
|
632 |
"model.layers.52.input_layernorm.weight": "model-00040-of-00061.safetensors",
|
633 |
"model.layers.52.mlp.down_proj.weight": "model-00040-of-00061.safetensors",
|
@@ -636,11 +444,7 @@
|
|
636 |
"model.layers.52.post_attention_layernorm.weight": "model-00040-of-00061.safetensors",
|
637 |
"model.layers.52.self_attn.k_proj.weight": "model-00040-of-00061.safetensors",
|
638 |
"model.layers.52.self_attn.o_proj.weight": "model-00040-of-00061.safetensors",
|
639 |
-
"model.layers.52.self_attn.q_proj.lora_A.default.weight": "model-00040-of-00061.safetensors",
|
640 |
-
"model.layers.52.self_attn.q_proj.lora_B.default.weight": "model-00040-of-00061.safetensors",
|
641 |
"model.layers.52.self_attn.q_proj.weight": "model-00040-of-00061.safetensors",
|
642 |
-
"model.layers.52.self_attn.v_proj.lora_A.default.weight": "model-00040-of-00061.safetensors",
|
643 |
-
"model.layers.52.self_attn.v_proj.lora_B.default.weight": "model-00040-of-00061.safetensors",
|
644 |
"model.layers.52.self_attn.v_proj.weight": "model-00040-of-00061.safetensors",
|
645 |
"model.layers.53.input_layernorm.weight": "model-00041-of-00061.safetensors",
|
646 |
"model.layers.53.mlp.down_proj.weight": "model-00041-of-00061.safetensors",
|
@@ -649,11 +453,7 @@
|
|
649 |
"model.layers.53.post_attention_layernorm.weight": "model-00041-of-00061.safetensors",
|
650 |
"model.layers.53.self_attn.k_proj.weight": "model-00040-of-00061.safetensors",
|
651 |
"model.layers.53.self_attn.o_proj.weight": "model-00040-of-00061.safetensors",
|
652 |
-
"model.layers.53.self_attn.q_proj.lora_A.default.weight": "model-00040-of-00061.safetensors",
|
653 |
-
"model.layers.53.self_attn.q_proj.lora_B.default.weight": "model-00040-of-00061.safetensors",
|
654 |
"model.layers.53.self_attn.q_proj.weight": "model-00040-of-00061.safetensors",
|
655 |
-
"model.layers.53.self_attn.v_proj.lora_A.default.weight": "model-00040-of-00061.safetensors",
|
656 |
-
"model.layers.53.self_attn.v_proj.lora_B.default.weight": "model-00040-of-00061.safetensors",
|
657 |
"model.layers.53.self_attn.v_proj.weight": "model-00040-of-00061.safetensors",
|
658 |
"model.layers.54.input_layernorm.weight": "model-00042-of-00061.safetensors",
|
659 |
"model.layers.54.mlp.down_proj.weight": "model-00042-of-00061.safetensors",
|
@@ -662,11 +462,7 @@
|
|
662 |
"model.layers.54.post_attention_layernorm.weight": "model-00042-of-00061.safetensors",
|
663 |
"model.layers.54.self_attn.k_proj.weight": "model-00041-of-00061.safetensors",
|
664 |
"model.layers.54.self_attn.o_proj.weight": "model-00041-of-00061.safetensors",
|
665 |
-
"model.layers.54.self_attn.q_proj.lora_A.default.weight": "model-00041-of-00061.safetensors",
|
666 |
-
"model.layers.54.self_attn.q_proj.lora_B.default.weight": "model-00041-of-00061.safetensors",
|
667 |
"model.layers.54.self_attn.q_proj.weight": "model-00041-of-00061.safetensors",
|
668 |
-
"model.layers.54.self_attn.v_proj.lora_A.default.weight": "model-00041-of-00061.safetensors",
|
669 |
-
"model.layers.54.self_attn.v_proj.lora_B.default.weight": "model-00041-of-00061.safetensors",
|
670 |
"model.layers.54.self_attn.v_proj.weight": "model-00041-of-00061.safetensors",
|
671 |
"model.layers.55.input_layernorm.weight": "model-00043-of-00061.safetensors",
|
672 |
"model.layers.55.mlp.down_proj.weight": "model-00043-of-00061.safetensors",
|
@@ -675,11 +471,7 @@
|
|
675 |
"model.layers.55.post_attention_layernorm.weight": "model-00043-of-00061.safetensors",
|
676 |
"model.layers.55.self_attn.k_proj.weight": "model-00042-of-00061.safetensors",
|
677 |
"model.layers.55.self_attn.o_proj.weight": "model-00042-of-00061.safetensors",
|
678 |
-
"model.layers.55.self_attn.q_proj.lora_A.default.weight": "model-00042-of-00061.safetensors",
|
679 |
-
"model.layers.55.self_attn.q_proj.lora_B.default.weight": "model-00042-of-00061.safetensors",
|
680 |
"model.layers.55.self_attn.q_proj.weight": "model-00042-of-00061.safetensors",
|
681 |
-
"model.layers.55.self_attn.v_proj.lora_A.default.weight": "model-00042-of-00061.safetensors",
|
682 |
-
"model.layers.55.self_attn.v_proj.lora_B.default.weight": "model-00042-of-00061.safetensors",
|
683 |
"model.layers.55.self_attn.v_proj.weight": "model-00042-of-00061.safetensors",
|
684 |
"model.layers.56.input_layernorm.weight": "model-00043-of-00061.safetensors",
|
685 |
"model.layers.56.mlp.down_proj.weight": "model-00043-of-00061.safetensors",
|
@@ -688,11 +480,7 @@
|
|
688 |
"model.layers.56.post_attention_layernorm.weight": "model-00043-of-00061.safetensors",
|
689 |
"model.layers.56.self_attn.k_proj.weight": "model-00043-of-00061.safetensors",
|
690 |
"model.layers.56.self_attn.o_proj.weight": "model-00043-of-00061.safetensors",
|
691 |
-
"model.layers.56.self_attn.q_proj.lora_A.default.weight": "model-00043-of-00061.safetensors",
|
692 |
-
"model.layers.56.self_attn.q_proj.lora_B.default.weight": "model-00043-of-00061.safetensors",
|
693 |
"model.layers.56.self_attn.q_proj.weight": "model-00043-of-00061.safetensors",
|
694 |
-
"model.layers.56.self_attn.v_proj.lora_A.default.weight": "model-00043-of-00061.safetensors",
|
695 |
-
"model.layers.56.self_attn.v_proj.lora_B.default.weight": "model-00043-of-00061.safetensors",
|
696 |
"model.layers.56.self_attn.v_proj.weight": "model-00043-of-00061.safetensors",
|
697 |
"model.layers.57.input_layernorm.weight": "model-00044-of-00061.safetensors",
|
698 |
"model.layers.57.mlp.down_proj.weight": "model-00044-of-00061.safetensors",
|
@@ -701,11 +489,7 @@
|
|
701 |
"model.layers.57.post_attention_layernorm.weight": "model-00044-of-00061.safetensors",
|
702 |
"model.layers.57.self_attn.k_proj.weight": "model-00043-of-00061.safetensors",
|
703 |
"model.layers.57.self_attn.o_proj.weight": "model-00043-of-00061.safetensors",
|
704 |
-
"model.layers.57.self_attn.q_proj.lora_A.default.weight": "model-00043-of-00061.safetensors",
|
705 |
-
"model.layers.57.self_attn.q_proj.lora_B.default.weight": "model-00043-of-00061.safetensors",
|
706 |
"model.layers.57.self_attn.q_proj.weight": "model-00043-of-00061.safetensors",
|
707 |
-
"model.layers.57.self_attn.v_proj.lora_A.default.weight": "model-00043-of-00061.safetensors",
|
708 |
-
"model.layers.57.self_attn.v_proj.lora_B.default.weight": "model-00043-of-00061.safetensors",
|
709 |
"model.layers.57.self_attn.v_proj.weight": "model-00043-of-00061.safetensors",
|
710 |
"model.layers.58.input_layernorm.weight": "model-00045-of-00061.safetensors",
|
711 |
"model.layers.58.mlp.down_proj.weight": "model-00045-of-00061.safetensors",
|
@@ -714,11 +498,7 @@
|
|
714 |
"model.layers.58.post_attention_layernorm.weight": "model-00045-of-00061.safetensors",
|
715 |
"model.layers.58.self_attn.k_proj.weight": "model-00044-of-00061.safetensors",
|
716 |
"model.layers.58.self_attn.o_proj.weight": "model-00044-of-00061.safetensors",
|
717 |
-
"model.layers.58.self_attn.q_proj.lora_A.default.weight": "model-00044-of-00061.safetensors",
|
718 |
-
"model.layers.58.self_attn.q_proj.lora_B.default.weight": "model-00044-of-00061.safetensors",
|
719 |
"model.layers.58.self_attn.q_proj.weight": "model-00044-of-00061.safetensors",
|
720 |
-
"model.layers.58.self_attn.v_proj.lora_A.default.weight": "model-00044-of-00061.safetensors",
|
721 |
-
"model.layers.58.self_attn.v_proj.lora_B.default.weight": "model-00044-of-00061.safetensors",
|
722 |
"model.layers.58.self_attn.v_proj.weight": "model-00044-of-00061.safetensors",
|
723 |
"model.layers.59.input_layernorm.weight": "model-00046-of-00061.safetensors",
|
724 |
"model.layers.59.mlp.down_proj.weight": "model-00046-of-00061.safetensors",
|
@@ -727,11 +507,7 @@
|
|
727 |
"model.layers.59.post_attention_layernorm.weight": "model-00046-of-00061.safetensors",
|
728 |
"model.layers.59.self_attn.k_proj.weight": "model-00045-of-00061.safetensors",
|
729 |
"model.layers.59.self_attn.o_proj.weight": "model-00045-of-00061.safetensors",
|
730 |
-
"model.layers.59.self_attn.q_proj.lora_A.default.weight": "model-00045-of-00061.safetensors",
|
731 |
-
"model.layers.59.self_attn.q_proj.lora_B.default.weight": "model-00045-of-00061.safetensors",
|
732 |
"model.layers.59.self_attn.q_proj.weight": "model-00045-of-00061.safetensors",
|
733 |
-
"model.layers.59.self_attn.v_proj.lora_A.default.weight": "model-00045-of-00061.safetensors",
|
734 |
-
"model.layers.59.self_attn.v_proj.lora_B.default.weight": "model-00045-of-00061.safetensors",
|
735 |
"model.layers.59.self_attn.v_proj.weight": "model-00045-of-00061.safetensors",
|
736 |
"model.layers.6.input_layernorm.weight": "model-00006-of-00061.safetensors",
|
737 |
"model.layers.6.mlp.down_proj.weight": "model-00006-of-00061.safetensors",
|
@@ -740,11 +516,7 @@
|
|
740 |
"model.layers.6.post_attention_layernorm.weight": "model-00006-of-00061.safetensors",
|
741 |
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00061.safetensors",
|
742 |
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00061.safetensors",
|
743 |
-
"model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00061.safetensors",
|
744 |
-
"model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00061.safetensors",
|
745 |
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00061.safetensors",
|
746 |
-
"model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00061.safetensors",
|
747 |
-
"model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00061.safetensors",
|
748 |
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00061.safetensors",
|
749 |
"model.layers.60.input_layernorm.weight": "model-00046-of-00061.safetensors",
|
750 |
"model.layers.60.mlp.down_proj.weight": "model-00046-of-00061.safetensors",
|
@@ -753,11 +525,7 @@
|
|
753 |
"model.layers.60.post_attention_layernorm.weight": "model-00046-of-00061.safetensors",
|
754 |
"model.layers.60.self_attn.k_proj.weight": "model-00046-of-00061.safetensors",
|
755 |
"model.layers.60.self_attn.o_proj.weight": "model-00046-of-00061.safetensors",
|
756 |
-
"model.layers.60.self_attn.q_proj.lora_A.default.weight": "model-00046-of-00061.safetensors",
|
757 |
-
"model.layers.60.self_attn.q_proj.lora_B.default.weight": "model-00046-of-00061.safetensors",
|
758 |
"model.layers.60.self_attn.q_proj.weight": "model-00046-of-00061.safetensors",
|
759 |
-
"model.layers.60.self_attn.v_proj.lora_A.default.weight": "model-00046-of-00061.safetensors",
|
760 |
-
"model.layers.60.self_attn.v_proj.lora_B.default.weight": "model-00046-of-00061.safetensors",
|
761 |
"model.layers.60.self_attn.v_proj.weight": "model-00046-of-00061.safetensors",
|
762 |
"model.layers.61.input_layernorm.weight": "model-00047-of-00061.safetensors",
|
763 |
"model.layers.61.mlp.down_proj.weight": "model-00047-of-00061.safetensors",
|
@@ -766,11 +534,7 @@
|
|
766 |
"model.layers.61.post_attention_layernorm.weight": "model-00047-of-00061.safetensors",
|
767 |
"model.layers.61.self_attn.k_proj.weight": "model-00046-of-00061.safetensors",
|
768 |
"model.layers.61.self_attn.o_proj.weight": "model-00046-of-00061.safetensors",
|
769 |
-
"model.layers.61.self_attn.q_proj.lora_A.default.weight": "model-00046-of-00061.safetensors",
|
770 |
-
"model.layers.61.self_attn.q_proj.lora_B.default.weight": "model-00046-of-00061.safetensors",
|
771 |
"model.layers.61.self_attn.q_proj.weight": "model-00046-of-00061.safetensors",
|
772 |
-
"model.layers.61.self_attn.v_proj.lora_A.default.weight": "model-00046-of-00061.safetensors",
|
773 |
-
"model.layers.61.self_attn.v_proj.lora_B.default.weight": "model-00046-of-00061.safetensors",
|
774 |
"model.layers.61.self_attn.v_proj.weight": "model-00046-of-00061.safetensors",
|
775 |
"model.layers.62.input_layernorm.weight": "model-00048-of-00061.safetensors",
|
776 |
"model.layers.62.mlp.down_proj.weight": "model-00048-of-00061.safetensors",
|
@@ -779,11 +543,7 @@
|
|
779 |
"model.layers.62.post_attention_layernorm.weight": "model-00048-of-00061.safetensors",
|
780 |
"model.layers.62.self_attn.k_proj.weight": "model-00047-of-00061.safetensors",
|
781 |
"model.layers.62.self_attn.o_proj.weight": "model-00047-of-00061.safetensors",
|
782 |
-
"model.layers.62.self_attn.q_proj.lora_A.default.weight": "model-00047-of-00061.safetensors",
|
783 |
-
"model.layers.62.self_attn.q_proj.lora_B.default.weight": "model-00047-of-00061.safetensors",
|
784 |
"model.layers.62.self_attn.q_proj.weight": "model-00047-of-00061.safetensors",
|
785 |
-
"model.layers.62.self_attn.v_proj.lora_A.default.weight": "model-00047-of-00061.safetensors",
|
786 |
-
"model.layers.62.self_attn.v_proj.lora_B.default.weight": "model-00047-of-00061.safetensors",
|
787 |
"model.layers.62.self_attn.v_proj.weight": "model-00047-of-00061.safetensors",
|
788 |
"model.layers.63.input_layernorm.weight": "model-00049-of-00061.safetensors",
|
789 |
"model.layers.63.mlp.down_proj.weight": "model-00049-of-00061.safetensors",
|
@@ -792,11 +552,7 @@
|
|
792 |
"model.layers.63.post_attention_layernorm.weight": "model-00049-of-00061.safetensors",
|
793 |
"model.layers.63.self_attn.k_proj.weight": "model-00048-of-00061.safetensors",
|
794 |
"model.layers.63.self_attn.o_proj.weight": "model-00048-of-00061.safetensors",
|
795 |
-
"model.layers.63.self_attn.q_proj.lora_A.default.weight": "model-00048-of-00061.safetensors",
|
796 |
-
"model.layers.63.self_attn.q_proj.lora_B.default.weight": "model-00048-of-00061.safetensors",
|
797 |
"model.layers.63.self_attn.q_proj.weight": "model-00048-of-00061.safetensors",
|
798 |
-
"model.layers.63.self_attn.v_proj.lora_A.default.weight": "model-00048-of-00061.safetensors",
|
799 |
-
"model.layers.63.self_attn.v_proj.lora_B.default.weight": "model-00048-of-00061.safetensors",
|
800 |
"model.layers.63.self_attn.v_proj.weight": "model-00048-of-00061.safetensors",
|
801 |
"model.layers.64.input_layernorm.weight": "model-00049-of-00061.safetensors",
|
802 |
"model.layers.64.mlp.down_proj.weight": "model-00049-of-00061.safetensors",
|
@@ -805,11 +561,7 @@
|
|
805 |
"model.layers.64.post_attention_layernorm.weight": "model-00049-of-00061.safetensors",
|
806 |
"model.layers.64.self_attn.k_proj.weight": "model-00049-of-00061.safetensors",
|
807 |
"model.layers.64.self_attn.o_proj.weight": "model-00049-of-00061.safetensors",
|
808 |
-
"model.layers.64.self_attn.q_proj.lora_A.default.weight": "model-00049-of-00061.safetensors",
|
809 |
-
"model.layers.64.self_attn.q_proj.lora_B.default.weight": "model-00049-of-00061.safetensors",
|
810 |
"model.layers.64.self_attn.q_proj.weight": "model-00049-of-00061.safetensors",
|
811 |
-
"model.layers.64.self_attn.v_proj.lora_A.default.weight": "model-00049-of-00061.safetensors",
|
812 |
-
"model.layers.64.self_attn.v_proj.lora_B.default.weight": "model-00049-of-00061.safetensors",
|
813 |
"model.layers.64.self_attn.v_proj.weight": "model-00049-of-00061.safetensors",
|
814 |
"model.layers.65.input_layernorm.weight": "model-00050-of-00061.safetensors",
|
815 |
"model.layers.65.mlp.down_proj.weight": "model-00050-of-00061.safetensors",
|
@@ -818,11 +570,7 @@
|
|
818 |
"model.layers.65.post_attention_layernorm.weight": "model-00050-of-00061.safetensors",
|
819 |
"model.layers.65.self_attn.k_proj.weight": "model-00049-of-00061.safetensors",
|
820 |
"model.layers.65.self_attn.o_proj.weight": "model-00049-of-00061.safetensors",
|
821 |
-
"model.layers.65.self_attn.q_proj.lora_A.default.weight": "model-00049-of-00061.safetensors",
|
822 |
-
"model.layers.65.self_attn.q_proj.lora_B.default.weight": "model-00049-of-00061.safetensors",
|
823 |
"model.layers.65.self_attn.q_proj.weight": "model-00049-of-00061.safetensors",
|
824 |
-
"model.layers.65.self_attn.v_proj.lora_A.default.weight": "model-00049-of-00061.safetensors",
|
825 |
-
"model.layers.65.self_attn.v_proj.lora_B.default.weight": "model-00049-of-00061.safetensors",
|
826 |
"model.layers.65.self_attn.v_proj.weight": "model-00049-of-00061.safetensors",
|
827 |
"model.layers.66.input_layernorm.weight": "model-00051-of-00061.safetensors",
|
828 |
"model.layers.66.mlp.down_proj.weight": "model-00051-of-00061.safetensors",
|
@@ -831,11 +579,7 @@
|
|
831 |
"model.layers.66.post_attention_layernorm.weight": "model-00051-of-00061.safetensors",
|
832 |
"model.layers.66.self_attn.k_proj.weight": "model-00050-of-00061.safetensors",
|
833 |
"model.layers.66.self_attn.o_proj.weight": "model-00050-of-00061.safetensors",
|
834 |
-
"model.layers.66.self_attn.q_proj.lora_A.default.weight": "model-00050-of-00061.safetensors",
|
835 |
-
"model.layers.66.self_attn.q_proj.lora_B.default.weight": "model-00050-of-00061.safetensors",
|
836 |
"model.layers.66.self_attn.q_proj.weight": "model-00050-of-00061.safetensors",
|
837 |
-
"model.layers.66.self_attn.v_proj.lora_A.default.weight": "model-00050-of-00061.safetensors",
|
838 |
-
"model.layers.66.self_attn.v_proj.lora_B.default.weight": "model-00050-of-00061.safetensors",
|
839 |
"model.layers.66.self_attn.v_proj.weight": "model-00050-of-00061.safetensors",
|
840 |
"model.layers.67.input_layernorm.weight": "model-00052-of-00061.safetensors",
|
841 |
"model.layers.67.mlp.down_proj.weight": "model-00052-of-00061.safetensors",
|
@@ -844,11 +588,7 @@
|
|
844 |
"model.layers.67.post_attention_layernorm.weight": "model-00052-of-00061.safetensors",
|
845 |
"model.layers.67.self_attn.k_proj.weight": "model-00051-of-00061.safetensors",
|
846 |
"model.layers.67.self_attn.o_proj.weight": "model-00051-of-00061.safetensors",
|
847 |
-
"model.layers.67.self_attn.q_proj.lora_A.default.weight": "model-00051-of-00061.safetensors",
|
848 |
-
"model.layers.67.self_attn.q_proj.lora_B.default.weight": "model-00051-of-00061.safetensors",
|
849 |
"model.layers.67.self_attn.q_proj.weight": "model-00051-of-00061.safetensors",
|
850 |
-
"model.layers.67.self_attn.v_proj.lora_A.default.weight": "model-00051-of-00061.safetensors",
|
851 |
-
"model.layers.67.self_attn.v_proj.lora_B.default.weight": "model-00051-of-00061.safetensors",
|
852 |
"model.layers.67.self_attn.v_proj.weight": "model-00051-of-00061.safetensors",
|
853 |
"model.layers.68.input_layernorm.weight": "model-00052-of-00061.safetensors",
|
854 |
"model.layers.68.mlp.down_proj.weight": "model-00052-of-00061.safetensors",
|
@@ -857,11 +597,7 @@
|
|
857 |
"model.layers.68.post_attention_layernorm.weight": "model-00052-of-00061.safetensors",
|
858 |
"model.layers.68.self_attn.k_proj.weight": "model-00052-of-00061.safetensors",
|
859 |
"model.layers.68.self_attn.o_proj.weight": "model-00052-of-00061.safetensors",
|
860 |
-
"model.layers.68.self_attn.q_proj.lora_A.default.weight": "model-00052-of-00061.safetensors",
|
861 |
-
"model.layers.68.self_attn.q_proj.lora_B.default.weight": "model-00052-of-00061.safetensors",
|
862 |
"model.layers.68.self_attn.q_proj.weight": "model-00052-of-00061.safetensors",
|
863 |
-
"model.layers.68.self_attn.v_proj.lora_A.default.weight": "model-00052-of-00061.safetensors",
|
864 |
-
"model.layers.68.self_attn.v_proj.lora_B.default.weight": "model-00052-of-00061.safetensors",
|
865 |
"model.layers.68.self_attn.v_proj.weight": "model-00052-of-00061.safetensors",
|
866 |
"model.layers.69.input_layernorm.weight": "model-00053-of-00061.safetensors",
|
867 |
"model.layers.69.mlp.down_proj.weight": "model-00053-of-00061.safetensors",
|
@@ -870,11 +606,7 @@
|
|
870 |
"model.layers.69.post_attention_layernorm.weight": "model-00053-of-00061.safetensors",
|
871 |
"model.layers.69.self_attn.k_proj.weight": "model-00052-of-00061.safetensors",
|
872 |
"model.layers.69.self_attn.o_proj.weight": "model-00052-of-00061.safetensors",
|
873 |
-
"model.layers.69.self_attn.q_proj.lora_A.default.weight": "model-00052-of-00061.safetensors",
|
874 |
-
"model.layers.69.self_attn.q_proj.lora_B.default.weight": "model-00052-of-00061.safetensors",
|
875 |
"model.layers.69.self_attn.q_proj.weight": "model-00052-of-00061.safetensors",
|
876 |
-
"model.layers.69.self_attn.v_proj.lora_A.default.weight": "model-00052-of-00061.safetensors",
|
877 |
-
"model.layers.69.self_attn.v_proj.lora_B.default.weight": "model-00052-of-00061.safetensors",
|
878 |
"model.layers.69.self_attn.v_proj.weight": "model-00052-of-00061.safetensors",
|
879 |
"model.layers.7.input_layernorm.weight": "model-00007-of-00061.safetensors",
|
880 |
"model.layers.7.mlp.down_proj.weight": "model-00007-of-00061.safetensors",
|
@@ -883,11 +615,7 @@
|
|
883 |
"model.layers.7.post_attention_layernorm.weight": "model-00007-of-00061.safetensors",
|
884 |
"model.layers.7.self_attn.k_proj.weight": "model-00006-of-00061.safetensors",
|
885 |
"model.layers.7.self_attn.o_proj.weight": "model-00006-of-00061.safetensors",
|
886 |
-
"model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00061.safetensors",
|
887 |
-
"model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00061.safetensors",
|
888 |
"model.layers.7.self_attn.q_proj.weight": "model-00006-of-00061.safetensors",
|
889 |
-
"model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00061.safetensors",
|
890 |
-
"model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00061.safetensors",
|
891 |
"model.layers.7.self_attn.v_proj.weight": "model-00006-of-00061.safetensors",
|
892 |
"model.layers.70.input_layernorm.weight": "model-00054-of-00061.safetensors",
|
893 |
"model.layers.70.mlp.down_proj.weight": "model-00054-of-00061.safetensors",
|
@@ -896,11 +624,7 @@
|
|
896 |
"model.layers.70.post_attention_layernorm.weight": "model-00054-of-00061.safetensors",
|
897 |
"model.layers.70.self_attn.k_proj.weight": "model-00053-of-00061.safetensors",
|
898 |
"model.layers.70.self_attn.o_proj.weight": "model-00053-of-00061.safetensors",
|
899 |
-
"model.layers.70.self_attn.q_proj.lora_A.default.weight": "model-00053-of-00061.safetensors",
|
900 |
-
"model.layers.70.self_attn.q_proj.lora_B.default.weight": "model-00053-of-00061.safetensors",
|
901 |
"model.layers.70.self_attn.q_proj.weight": "model-00053-of-00061.safetensors",
|
902 |
-
"model.layers.70.self_attn.v_proj.lora_A.default.weight": "model-00053-of-00061.safetensors",
|
903 |
-
"model.layers.70.self_attn.v_proj.lora_B.default.weight": "model-00053-of-00061.safetensors",
|
904 |
"model.layers.70.self_attn.v_proj.weight": "model-00053-of-00061.safetensors",
|
905 |
"model.layers.71.input_layernorm.weight": "model-00055-of-00061.safetensors",
|
906 |
"model.layers.71.mlp.down_proj.weight": "model-00055-of-00061.safetensors",
|
@@ -909,11 +633,7 @@
|
|
909 |
"model.layers.71.post_attention_layernorm.weight": "model-00055-of-00061.safetensors",
|
910 |
"model.layers.71.self_attn.k_proj.weight": "model-00054-of-00061.safetensors",
|
911 |
"model.layers.71.self_attn.o_proj.weight": "model-00054-of-00061.safetensors",
|
912 |
-
"model.layers.71.self_attn.q_proj.lora_A.default.weight": "model-00054-of-00061.safetensors",
|
913 |
-
"model.layers.71.self_attn.q_proj.lora_B.default.weight": "model-00054-of-00061.safetensors",
|
914 |
"model.layers.71.self_attn.q_proj.weight": "model-00054-of-00061.safetensors",
|
915 |
-
"model.layers.71.self_attn.v_proj.lora_A.default.weight": "model-00054-of-00061.safetensors",
|
916 |
-
"model.layers.71.self_attn.v_proj.lora_B.default.weight": "model-00054-of-00061.safetensors",
|
917 |
"model.layers.71.self_attn.v_proj.weight": "model-00054-of-00061.safetensors",
|
918 |
"model.layers.72.input_layernorm.weight": "model-00055-of-00061.safetensors",
|
919 |
"model.layers.72.mlp.down_proj.weight": "model-00055-of-00061.safetensors",
|
@@ -922,11 +642,7 @@
|
|
922 |
"model.layers.72.post_attention_layernorm.weight": "model-00055-of-00061.safetensors",
|
923 |
"model.layers.72.self_attn.k_proj.weight": "model-00055-of-00061.safetensors",
|
924 |
"model.layers.72.self_attn.o_proj.weight": "model-00055-of-00061.safetensors",
|
925 |
-
"model.layers.72.self_attn.q_proj.lora_A.default.weight": "model-00055-of-00061.safetensors",
|
926 |
-
"model.layers.72.self_attn.q_proj.lora_B.default.weight": "model-00055-of-00061.safetensors",
|
927 |
"model.layers.72.self_attn.q_proj.weight": "model-00055-of-00061.safetensors",
|
928 |
-
"model.layers.72.self_attn.v_proj.lora_A.default.weight": "model-00055-of-00061.safetensors",
|
929 |
-
"model.layers.72.self_attn.v_proj.lora_B.default.weight": "model-00055-of-00061.safetensors",
|
930 |
"model.layers.72.self_attn.v_proj.weight": "model-00055-of-00061.safetensors",
|
931 |
"model.layers.73.input_layernorm.weight": "model-00056-of-00061.safetensors",
|
932 |
"model.layers.73.mlp.down_proj.weight": "model-00056-of-00061.safetensors",
|
@@ -935,11 +651,7 @@
|
|
935 |
"model.layers.73.post_attention_layernorm.weight": "model-00056-of-00061.safetensors",
|
936 |
"model.layers.73.self_attn.k_proj.weight": "model-00055-of-00061.safetensors",
|
937 |
"model.layers.73.self_attn.o_proj.weight": "model-00055-of-00061.safetensors",
|
938 |
-
"model.layers.73.self_attn.q_proj.lora_A.default.weight": "model-00055-of-00061.safetensors",
|
939 |
-
"model.layers.73.self_attn.q_proj.lora_B.default.weight": "model-00055-of-00061.safetensors",
|
940 |
"model.layers.73.self_attn.q_proj.weight": "model-00055-of-00061.safetensors",
|
941 |
-
"model.layers.73.self_attn.v_proj.lora_A.default.weight": "model-00055-of-00061.safetensors",
|
942 |
-
"model.layers.73.self_attn.v_proj.lora_B.default.weight": "model-00055-of-00061.safetensors",
|
943 |
"model.layers.73.self_attn.v_proj.weight": "model-00055-of-00061.safetensors",
|
944 |
"model.layers.74.input_layernorm.weight": "model-00057-of-00061.safetensors",
|
945 |
"model.layers.74.mlp.down_proj.weight": "model-00057-of-00061.safetensors",
|
@@ -948,11 +660,7 @@
|
|
948 |
"model.layers.74.post_attention_layernorm.weight": "model-00057-of-00061.safetensors",
|
949 |
"model.layers.74.self_attn.k_proj.weight": "model-00056-of-00061.safetensors",
|
950 |
"model.layers.74.self_attn.o_proj.weight": "model-00056-of-00061.safetensors",
|
951 |
-
"model.layers.74.self_attn.q_proj.lora_A.default.weight": "model-00056-of-00061.safetensors",
|
952 |
-
"model.layers.74.self_attn.q_proj.lora_B.default.weight": "model-00056-of-00061.safetensors",
|
953 |
"model.layers.74.self_attn.q_proj.weight": "model-00056-of-00061.safetensors",
|
954 |
-
"model.layers.74.self_attn.v_proj.lora_A.default.weight": "model-00056-of-00061.safetensors",
|
955 |
-
"model.layers.74.self_attn.v_proj.lora_B.default.weight": "model-00056-of-00061.safetensors",
|
956 |
"model.layers.74.self_attn.v_proj.weight": "model-00056-of-00061.safetensors",
|
957 |
"model.layers.75.input_layernorm.weight": "model-00058-of-00061.safetensors",
|
958 |
"model.layers.75.mlp.down_proj.weight": "model-00058-of-00061.safetensors",
|
@@ -961,11 +669,7 @@
|
|
961 |
"model.layers.75.post_attention_layernorm.weight": "model-00058-of-00061.safetensors",
|
962 |
"model.layers.75.self_attn.k_proj.weight": "model-00057-of-00061.safetensors",
|
963 |
"model.layers.75.self_attn.o_proj.weight": "model-00057-of-00061.safetensors",
|
964 |
-
"model.layers.75.self_attn.q_proj.lora_A.default.weight": "model-00057-of-00061.safetensors",
|
965 |
-
"model.layers.75.self_attn.q_proj.lora_B.default.weight": "model-00057-of-00061.safetensors",
|
966 |
"model.layers.75.self_attn.q_proj.weight": "model-00057-of-00061.safetensors",
|
967 |
-
"model.layers.75.self_attn.v_proj.lora_A.default.weight": "model-00057-of-00061.safetensors",
|
968 |
-
"model.layers.75.self_attn.v_proj.lora_B.default.weight": "model-00057-of-00061.safetensors",
|
969 |
"model.layers.75.self_attn.v_proj.weight": "model-00057-of-00061.safetensors",
|
970 |
"model.layers.76.input_layernorm.weight": "model-00058-of-00061.safetensors",
|
971 |
"model.layers.76.mlp.down_proj.weight": "model-00058-of-00061.safetensors",
|
@@ -974,11 +678,7 @@
|
|
974 |
"model.layers.76.post_attention_layernorm.weight": "model-00058-of-00061.safetensors",
|
975 |
"model.layers.76.self_attn.k_proj.weight": "model-00058-of-00061.safetensors",
|
976 |
"model.layers.76.self_attn.o_proj.weight": "model-00058-of-00061.safetensors",
|
977 |
-
"model.layers.76.self_attn.q_proj.lora_A.default.weight": "model-00058-of-00061.safetensors",
|
978 |
-
"model.layers.76.self_attn.q_proj.lora_B.default.weight": "model-00058-of-00061.safetensors",
|
979 |
"model.layers.76.self_attn.q_proj.weight": "model-00058-of-00061.safetensors",
|
980 |
-
"model.layers.76.self_attn.v_proj.lora_A.default.weight": "model-00058-of-00061.safetensors",
|
981 |
-
"model.layers.76.self_attn.v_proj.lora_B.default.weight": "model-00058-of-00061.safetensors",
|
982 |
"model.layers.76.self_attn.v_proj.weight": "model-00058-of-00061.safetensors",
|
983 |
"model.layers.77.input_layernorm.weight": "model-00059-of-00061.safetensors",
|
984 |
"model.layers.77.mlp.down_proj.weight": "model-00059-of-00061.safetensors",
|
@@ -987,11 +687,7 @@
|
|
987 |
"model.layers.77.post_attention_layernorm.weight": "model-00059-of-00061.safetensors",
|
988 |
"model.layers.77.self_attn.k_proj.weight": "model-00058-of-00061.safetensors",
|
989 |
"model.layers.77.self_attn.o_proj.weight": "model-00058-of-00061.safetensors",
|
990 |
-
"model.layers.77.self_attn.q_proj.lora_A.default.weight": "model-00058-of-00061.safetensors",
|
991 |
-
"model.layers.77.self_attn.q_proj.lora_B.default.weight": "model-00058-of-00061.safetensors",
|
992 |
"model.layers.77.self_attn.q_proj.weight": "model-00058-of-00061.safetensors",
|
993 |
-
"model.layers.77.self_attn.v_proj.lora_A.default.weight": "model-00058-of-00061.safetensors",
|
994 |
-
"model.layers.77.self_attn.v_proj.lora_B.default.weight": "model-00058-of-00061.safetensors",
|
995 |
"model.layers.77.self_attn.v_proj.weight": "model-00058-of-00061.safetensors",
|
996 |
"model.layers.78.input_layernorm.weight": "model-00060-of-00061.safetensors",
|
997 |
"model.layers.78.mlp.down_proj.weight": "model-00060-of-00061.safetensors",
|
@@ -1000,11 +696,7 @@
|
|
1000 |
"model.layers.78.post_attention_layernorm.weight": "model-00060-of-00061.safetensors",
|
1001 |
"model.layers.78.self_attn.k_proj.weight": "model-00059-of-00061.safetensors",
|
1002 |
"model.layers.78.self_attn.o_proj.weight": "model-00059-of-00061.safetensors",
|
1003 |
-
"model.layers.78.self_attn.q_proj.lora_A.default.weight": "model-00059-of-00061.safetensors",
|
1004 |
-
"model.layers.78.self_attn.q_proj.lora_B.default.weight": "model-00059-of-00061.safetensors",
|
1005 |
"model.layers.78.self_attn.q_proj.weight": "model-00059-of-00061.safetensors",
|
1006 |
-
"model.layers.78.self_attn.v_proj.lora_A.default.weight": "model-00059-of-00061.safetensors",
|
1007 |
-
"model.layers.78.self_attn.v_proj.lora_B.default.weight": "model-00059-of-00061.safetensors",
|
1008 |
"model.layers.78.self_attn.v_proj.weight": "model-00059-of-00061.safetensors",
|
1009 |
"model.layers.79.input_layernorm.weight": "model-00061-of-00061.safetensors",
|
1010 |
"model.layers.79.mlp.down_proj.weight": "model-00061-of-00061.safetensors",
|
@@ -1013,11 +705,7 @@
|
|
1013 |
"model.layers.79.post_attention_layernorm.weight": "model-00061-of-00061.safetensors",
|
1014 |
"model.layers.79.self_attn.k_proj.weight": "model-00060-of-00061.safetensors",
|
1015 |
"model.layers.79.self_attn.o_proj.weight": "model-00060-of-00061.safetensors",
|
1016 |
-
"model.layers.79.self_attn.q_proj.lora_A.default.weight": "model-00060-of-00061.safetensors",
|
1017 |
-
"model.layers.79.self_attn.q_proj.lora_B.default.weight": "model-00060-of-00061.safetensors",
|
1018 |
"model.layers.79.self_attn.q_proj.weight": "model-00060-of-00061.safetensors",
|
1019 |
-
"model.layers.79.self_attn.v_proj.lora_A.default.weight": "model-00060-of-00061.safetensors",
|
1020 |
-
"model.layers.79.self_attn.v_proj.lora_B.default.weight": "model-00060-of-00061.safetensors",
|
1021 |
"model.layers.79.self_attn.v_proj.weight": "model-00060-of-00061.safetensors",
|
1022 |
"model.layers.8.input_layernorm.weight": "model-00007-of-00061.safetensors",
|
1023 |
"model.layers.8.mlp.down_proj.weight": "model-00007-of-00061.safetensors",
|
@@ -1026,11 +714,7 @@
|
|
1026 |
"model.layers.8.post_attention_layernorm.weight": "model-00007-of-00061.safetensors",
|
1027 |
"model.layers.8.self_attn.k_proj.weight": "model-00007-of-00061.safetensors",
|
1028 |
"model.layers.8.self_attn.o_proj.weight": "model-00007-of-00061.safetensors",
|
1029 |
-
"model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00061.safetensors",
|
1030 |
-
"model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00061.safetensors",
|
1031 |
"model.layers.8.self_attn.q_proj.weight": "model-00007-of-00061.safetensors",
|
1032 |
-
"model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00061.safetensors",
|
1033 |
-
"model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00061.safetensors",
|
1034 |
"model.layers.8.self_attn.v_proj.weight": "model-00007-of-00061.safetensors",
|
1035 |
"model.layers.9.input_layernorm.weight": "model-00008-of-00061.safetensors",
|
1036 |
"model.layers.9.mlp.down_proj.weight": "model-00008-of-00061.safetensors",
|
@@ -1039,11 +723,7 @@
|
|
1039 |
"model.layers.9.post_attention_layernorm.weight": "model-00008-of-00061.safetensors",
|
1040 |
"model.layers.9.self_attn.k_proj.weight": "model-00007-of-00061.safetensors",
|
1041 |
"model.layers.9.self_attn.o_proj.weight": "model-00007-of-00061.safetensors",
|
1042 |
-
"model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00061.safetensors",
|
1043 |
-
"model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00061.safetensors",
|
1044 |
"model.layers.9.self_attn.q_proj.weight": "model-00007-of-00061.safetensors",
|
1045 |
-
"model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00061.safetensors",
|
1046 |
-
"model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00061.safetensors",
|
1047 |
"model.layers.9.self_attn.v_proj.weight": "model-00007-of-00061.safetensors",
|
1048 |
"model.norm.weight": "model-00061-of-00061.safetensors"
|
1049 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 275906592768
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00061-of-00061.safetensors",
|
|
|
12 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00061.safetensors",
|
13 |
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00061.safetensors",
|
14 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00061.safetensors",
|
|
|
|
|
15 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00061.safetensors",
|
|
|
|
|
16 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00061.safetensors",
|
17 |
"model.layers.1.input_layernorm.weight": "model-00002-of-00061.safetensors",
|
18 |
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00061.safetensors",
|
|
|
21 |
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00061.safetensors",
|
22 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00061.safetensors",
|
23 |
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00061.safetensors",
|
|
|
|
|
24 |
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00061.safetensors",
|
|
|
|
|
25 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00061.safetensors",
|
26 |
"model.layers.10.input_layernorm.weight": "model-00009-of-00061.safetensors",
|
27 |
"model.layers.10.mlp.down_proj.weight": "model-00009-of-00061.safetensors",
|
|
|
30 |
"model.layers.10.post_attention_layernorm.weight": "model-00009-of-00061.safetensors",
|
31 |
"model.layers.10.self_attn.k_proj.weight": "model-00008-of-00061.safetensors",
|
32 |
"model.layers.10.self_attn.o_proj.weight": "model-00008-of-00061.safetensors",
|
|
|
|
|
33 |
"model.layers.10.self_attn.q_proj.weight": "model-00008-of-00061.safetensors",
|
|
|
|
|
34 |
"model.layers.10.self_attn.v_proj.weight": "model-00008-of-00061.safetensors",
|
35 |
"model.layers.11.input_layernorm.weight": "model-00010-of-00061.safetensors",
|
36 |
"model.layers.11.mlp.down_proj.weight": "model-00010-of-00061.safetensors",
|
|
|
39 |
"model.layers.11.post_attention_layernorm.weight": "model-00010-of-00061.safetensors",
|
40 |
"model.layers.11.self_attn.k_proj.weight": "model-00009-of-00061.safetensors",
|
41 |
"model.layers.11.self_attn.o_proj.weight": "model-00009-of-00061.safetensors",
|
|
|
|
|
42 |
"model.layers.11.self_attn.q_proj.weight": "model-00009-of-00061.safetensors",
|
|
|
|
|
43 |
"model.layers.11.self_attn.v_proj.weight": "model-00009-of-00061.safetensors",
|
44 |
"model.layers.12.input_layernorm.weight": "model-00010-of-00061.safetensors",
|
45 |
"model.layers.12.mlp.down_proj.weight": "model-00010-of-00061.safetensors",
|
|
|
48 |
"model.layers.12.post_attention_layernorm.weight": "model-00010-of-00061.safetensors",
|
49 |
"model.layers.12.self_attn.k_proj.weight": "model-00010-of-00061.safetensors",
|
50 |
"model.layers.12.self_attn.o_proj.weight": "model-00010-of-00061.safetensors",
|
|
|
|
|
51 |
"model.layers.12.self_attn.q_proj.weight": "model-00010-of-00061.safetensors",
|
|
|
|
|
52 |
"model.layers.12.self_attn.v_proj.weight": "model-00010-of-00061.safetensors",
|
53 |
"model.layers.13.input_layernorm.weight": "model-00011-of-00061.safetensors",
|
54 |
"model.layers.13.mlp.down_proj.weight": "model-00011-of-00061.safetensors",
|
|
|
57 |
"model.layers.13.post_attention_layernorm.weight": "model-00011-of-00061.safetensors",
|
58 |
"model.layers.13.self_attn.k_proj.weight": "model-00010-of-00061.safetensors",
|
59 |
"model.layers.13.self_attn.o_proj.weight": "model-00010-of-00061.safetensors",
|
|
|
|
|
60 |
"model.layers.13.self_attn.q_proj.weight": "model-00010-of-00061.safetensors",
|
|
|
|
|
61 |
"model.layers.13.self_attn.v_proj.weight": "model-00010-of-00061.safetensors",
|
62 |
"model.layers.14.input_layernorm.weight": "model-00012-of-00061.safetensors",
|
63 |
"model.layers.14.mlp.down_proj.weight": "model-00012-of-00061.safetensors",
|
|
|
66 |
"model.layers.14.post_attention_layernorm.weight": "model-00012-of-00061.safetensors",
|
67 |
"model.layers.14.self_attn.k_proj.weight": "model-00011-of-00061.safetensors",
|
68 |
"model.layers.14.self_attn.o_proj.weight": "model-00011-of-00061.safetensors",
|
|
|
|
|
69 |
"model.layers.14.self_attn.q_proj.weight": "model-00011-of-00061.safetensors",
|
|
|
|
|
70 |
"model.layers.14.self_attn.v_proj.weight": "model-00011-of-00061.safetensors",
|
71 |
"model.layers.15.input_layernorm.weight": "model-00013-of-00061.safetensors",
|
72 |
"model.layers.15.mlp.down_proj.weight": "model-00013-of-00061.safetensors",
|
|
|
75 |
"model.layers.15.post_attention_layernorm.weight": "model-00013-of-00061.safetensors",
|
76 |
"model.layers.15.self_attn.k_proj.weight": "model-00012-of-00061.safetensors",
|
77 |
"model.layers.15.self_attn.o_proj.weight": "model-00012-of-00061.safetensors",
|
|
|
|
|
78 |
"model.layers.15.self_attn.q_proj.weight": "model-00012-of-00061.safetensors",
|
|
|
|
|
79 |
"model.layers.15.self_attn.v_proj.weight": "model-00012-of-00061.safetensors",
|
80 |
"model.layers.16.input_layernorm.weight": "model-00013-of-00061.safetensors",
|
81 |
"model.layers.16.mlp.down_proj.weight": "model-00013-of-00061.safetensors",
|
|
|
84 |
"model.layers.16.post_attention_layernorm.weight": "model-00013-of-00061.safetensors",
|
85 |
"model.layers.16.self_attn.k_proj.weight": "model-00013-of-00061.safetensors",
|
86 |
"model.layers.16.self_attn.o_proj.weight": "model-00013-of-00061.safetensors",
|
|
|
|
|
87 |
"model.layers.16.self_attn.q_proj.weight": "model-00013-of-00061.safetensors",
|
|
|
|
|
88 |
"model.layers.16.self_attn.v_proj.weight": "model-00013-of-00061.safetensors",
|
89 |
"model.layers.17.input_layernorm.weight": "model-00014-of-00061.safetensors",
|
90 |
"model.layers.17.mlp.down_proj.weight": "model-00014-of-00061.safetensors",
|
|
|
93 |
"model.layers.17.post_attention_layernorm.weight": "model-00014-of-00061.safetensors",
|
94 |
"model.layers.17.self_attn.k_proj.weight": "model-00013-of-00061.safetensors",
|
95 |
"model.layers.17.self_attn.o_proj.weight": "model-00013-of-00061.safetensors",
|
|
|
|
|
96 |
"model.layers.17.self_attn.q_proj.weight": "model-00013-of-00061.safetensors",
|
|
|
|
|
97 |
"model.layers.17.self_attn.v_proj.weight": "model-00013-of-00061.safetensors",
|
98 |
"model.layers.18.input_layernorm.weight": "model-00015-of-00061.safetensors",
|
99 |
"model.layers.18.mlp.down_proj.weight": "model-00015-of-00061.safetensors",
|
|
|
102 |
"model.layers.18.post_attention_layernorm.weight": "model-00015-of-00061.safetensors",
|
103 |
"model.layers.18.self_attn.k_proj.weight": "model-00014-of-00061.safetensors",
|
104 |
"model.layers.18.self_attn.o_proj.weight": "model-00014-of-00061.safetensors",
|
|
|
|
|
105 |
"model.layers.18.self_attn.q_proj.weight": "model-00014-of-00061.safetensors",
|
|
|
|
|
106 |
"model.layers.18.self_attn.v_proj.weight": "model-00014-of-00061.safetensors",
|
107 |
"model.layers.19.input_layernorm.weight": "model-00016-of-00061.safetensors",
|
108 |
"model.layers.19.mlp.down_proj.weight": "model-00016-of-00061.safetensors",
|
|
|
111 |
"model.layers.19.post_attention_layernorm.weight": "model-00016-of-00061.safetensors",
|
112 |
"model.layers.19.self_attn.k_proj.weight": "model-00015-of-00061.safetensors",
|
113 |
"model.layers.19.self_attn.o_proj.weight": "model-00015-of-00061.safetensors",
|
|
|
|
|
114 |
"model.layers.19.self_attn.q_proj.weight": "model-00015-of-00061.safetensors",
|
|
|
|
|
115 |
"model.layers.19.self_attn.v_proj.weight": "model-00015-of-00061.safetensors",
|
116 |
"model.layers.2.input_layernorm.weight": "model-00003-of-00061.safetensors",
|
117 |
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00061.safetensors",
|
|
|
120 |
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00061.safetensors",
|
121 |
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00061.safetensors",
|
122 |
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00061.safetensors",
|
|
|
|
|
123 |
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00061.safetensors",
|
|
|
|
|
124 |
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00061.safetensors",
|
125 |
"model.layers.20.input_layernorm.weight": "model-00016-of-00061.safetensors",
|
126 |
"model.layers.20.mlp.down_proj.weight": "model-00016-of-00061.safetensors",
|
|
|
129 |
"model.layers.20.post_attention_layernorm.weight": "model-00016-of-00061.safetensors",
|
130 |
"model.layers.20.self_attn.k_proj.weight": "model-00016-of-00061.safetensors",
|
131 |
"model.layers.20.self_attn.o_proj.weight": "model-00016-of-00061.safetensors",
|
|
|
|
|
132 |
"model.layers.20.self_attn.q_proj.weight": "model-00016-of-00061.safetensors",
|
|
|
|
|
133 |
"model.layers.20.self_attn.v_proj.weight": "model-00016-of-00061.safetensors",
|
134 |
"model.layers.21.input_layernorm.weight": "model-00017-of-00061.safetensors",
|
135 |
"model.layers.21.mlp.down_proj.weight": "model-00017-of-00061.safetensors",
|
|
|
138 |
"model.layers.21.post_attention_layernorm.weight": "model-00017-of-00061.safetensors",
|
139 |
"model.layers.21.self_attn.k_proj.weight": "model-00016-of-00061.safetensors",
|
140 |
"model.layers.21.self_attn.o_proj.weight": "model-00016-of-00061.safetensors",
|
|
|
|
|
141 |
"model.layers.21.self_attn.q_proj.weight": "model-00016-of-00061.safetensors",
|
|
|
|
|
142 |
"model.layers.21.self_attn.v_proj.weight": "model-00016-of-00061.safetensors",
|
143 |
"model.layers.22.input_layernorm.weight": "model-00018-of-00061.safetensors",
|
144 |
"model.layers.22.mlp.down_proj.weight": "model-00018-of-00061.safetensors",
|
|
|
147 |
"model.layers.22.post_attention_layernorm.weight": "model-00018-of-00061.safetensors",
|
148 |
"model.layers.22.self_attn.k_proj.weight": "model-00017-of-00061.safetensors",
|
149 |
"model.layers.22.self_attn.o_proj.weight": "model-00017-of-00061.safetensors",
|
|
|
|
|
150 |
"model.layers.22.self_attn.q_proj.weight": "model-00017-of-00061.safetensors",
|
|
|
|
|
151 |
"model.layers.22.self_attn.v_proj.weight": "model-00017-of-00061.safetensors",
|
152 |
"model.layers.23.input_layernorm.weight": "model-00019-of-00061.safetensors",
|
153 |
"model.layers.23.mlp.down_proj.weight": "model-00019-of-00061.safetensors",
|
|
|
156 |
"model.layers.23.post_attention_layernorm.weight": "model-00019-of-00061.safetensors",
|
157 |
"model.layers.23.self_attn.k_proj.weight": "model-00018-of-00061.safetensors",
|
158 |
"model.layers.23.self_attn.o_proj.weight": "model-00018-of-00061.safetensors",
|
|
|
|
|
159 |
"model.layers.23.self_attn.q_proj.weight": "model-00018-of-00061.safetensors",
|
|
|
|
|
160 |
"model.layers.23.self_attn.v_proj.weight": "model-00018-of-00061.safetensors",
|
161 |
"model.layers.24.input_layernorm.weight": "model-00019-of-00061.safetensors",
|
162 |
"model.layers.24.mlp.down_proj.weight": "model-00019-of-00061.safetensors",
|
|
|
165 |
"model.layers.24.post_attention_layernorm.weight": "model-00019-of-00061.safetensors",
|
166 |
"model.layers.24.self_attn.k_proj.weight": "model-00019-of-00061.safetensors",
|
167 |
"model.layers.24.self_attn.o_proj.weight": "model-00019-of-00061.safetensors",
|
|
|
|
|
168 |
"model.layers.24.self_attn.q_proj.weight": "model-00019-of-00061.safetensors",
|
|
|
|
|
169 |
"model.layers.24.self_attn.v_proj.weight": "model-00019-of-00061.safetensors",
|
170 |
"model.layers.25.input_layernorm.weight": "model-00020-of-00061.safetensors",
|
171 |
"model.layers.25.mlp.down_proj.weight": "model-00020-of-00061.safetensors",
|
|
|
174 |
"model.layers.25.post_attention_layernorm.weight": "model-00020-of-00061.safetensors",
|
175 |
"model.layers.25.self_attn.k_proj.weight": "model-00019-of-00061.safetensors",
|
176 |
"model.layers.25.self_attn.o_proj.weight": "model-00019-of-00061.safetensors",
|
|
|
|
|
177 |
"model.layers.25.self_attn.q_proj.weight": "model-00019-of-00061.safetensors",
|
|
|
|
|
178 |
"model.layers.25.self_attn.v_proj.weight": "model-00019-of-00061.safetensors",
|
179 |
"model.layers.26.input_layernorm.weight": "model-00021-of-00061.safetensors",
|
180 |
"model.layers.26.mlp.down_proj.weight": "model-00021-of-00061.safetensors",
|
|
|
183 |
"model.layers.26.post_attention_layernorm.weight": "model-00021-of-00061.safetensors",
|
184 |
"model.layers.26.self_attn.k_proj.weight": "model-00020-of-00061.safetensors",
|
185 |
"model.layers.26.self_attn.o_proj.weight": "model-00020-of-00061.safetensors",
|
|
|
|
|
186 |
"model.layers.26.self_attn.q_proj.weight": "model-00020-of-00061.safetensors",
|
|
|
|
|
187 |
"model.layers.26.self_attn.v_proj.weight": "model-00020-of-00061.safetensors",
|
188 |
"model.layers.27.input_layernorm.weight": "model-00022-of-00061.safetensors",
|
189 |
"model.layers.27.mlp.down_proj.weight": "model-00022-of-00061.safetensors",
|
|
|
192 |
"model.layers.27.post_attention_layernorm.weight": "model-00022-of-00061.safetensors",
|
193 |
"model.layers.27.self_attn.k_proj.weight": "model-00021-of-00061.safetensors",
|
194 |
"model.layers.27.self_attn.o_proj.weight": "model-00021-of-00061.safetensors",
|
|
|
|
|
195 |
"model.layers.27.self_attn.q_proj.weight": "model-00021-of-00061.safetensors",
|
|
|
|
|
196 |
"model.layers.27.self_attn.v_proj.weight": "model-00021-of-00061.safetensors",
|
197 |
"model.layers.28.input_layernorm.weight": "model-00022-of-00061.safetensors",
|
198 |
"model.layers.28.mlp.down_proj.weight": "model-00022-of-00061.safetensors",
|
|
|
201 |
"model.layers.28.post_attention_layernorm.weight": "model-00022-of-00061.safetensors",
|
202 |
"model.layers.28.self_attn.k_proj.weight": "model-00022-of-00061.safetensors",
|
203 |
"model.layers.28.self_attn.o_proj.weight": "model-00022-of-00061.safetensors",
|
|
|
|
|
204 |
"model.layers.28.self_attn.q_proj.weight": "model-00022-of-00061.safetensors",
|
|
|
|
|
205 |
"model.layers.28.self_attn.v_proj.weight": "model-00022-of-00061.safetensors",
|
206 |
"model.layers.29.input_layernorm.weight": "model-00023-of-00061.safetensors",
|
207 |
"model.layers.29.mlp.down_proj.weight": "model-00023-of-00061.safetensors",
|
|
|
210 |
"model.layers.29.post_attention_layernorm.weight": "model-00023-of-00061.safetensors",
|
211 |
"model.layers.29.self_attn.k_proj.weight": "model-00022-of-00061.safetensors",
|
212 |
"model.layers.29.self_attn.o_proj.weight": "model-00022-of-00061.safetensors",
|
|
|
|
|
213 |
"model.layers.29.self_attn.q_proj.weight": "model-00022-of-00061.safetensors",
|
|
|
|
|
214 |
"model.layers.29.self_attn.v_proj.weight": "model-00022-of-00061.safetensors",
|
215 |
"model.layers.3.input_layernorm.weight": "model-00004-of-00061.safetensors",
|
216 |
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00061.safetensors",
|
|
|
219 |
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00061.safetensors",
|
220 |
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00061.safetensors",
|
221 |
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00061.safetensors",
|
|
|
|
|
222 |
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00061.safetensors",
|
|
|
|
|
223 |
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00061.safetensors",
|
224 |
"model.layers.30.input_layernorm.weight": "model-00024-of-00061.safetensors",
|
225 |
"model.layers.30.mlp.down_proj.weight": "model-00024-of-00061.safetensors",
|
|
|
228 |
"model.layers.30.post_attention_layernorm.weight": "model-00024-of-00061.safetensors",
|
229 |
"model.layers.30.self_attn.k_proj.weight": "model-00023-of-00061.safetensors",
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00023-of-00061.safetensors",
|
|
|
|
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00023-of-00061.safetensors",
|
|
|
|
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00023-of-00061.safetensors",
|
233 |
"model.layers.31.input_layernorm.weight": "model-00025-of-00061.safetensors",
|
234 |
"model.layers.31.mlp.down_proj.weight": "model-00025-of-00061.safetensors",
|
|
|
237 |
"model.layers.31.post_attention_layernorm.weight": "model-00025-of-00061.safetensors",
|
238 |
"model.layers.31.self_attn.k_proj.weight": "model-00024-of-00061.safetensors",
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00024-of-00061.safetensors",
|
|
|
|
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00024-of-00061.safetensors",
|
|
|
|
|
241 |
"model.layers.31.self_attn.v_proj.weight": "model-00024-of-00061.safetensors",
|
242 |
"model.layers.32.input_layernorm.weight": "model-00025-of-00061.safetensors",
|
243 |
"model.layers.32.mlp.down_proj.weight": "model-00025-of-00061.safetensors",
|
|
|
246 |
"model.layers.32.post_attention_layernorm.weight": "model-00025-of-00061.safetensors",
|
247 |
"model.layers.32.self_attn.k_proj.weight": "model-00025-of-00061.safetensors",
|
248 |
"model.layers.32.self_attn.o_proj.weight": "model-00025-of-00061.safetensors",
|
|
|
|
|
249 |
"model.layers.32.self_attn.q_proj.weight": "model-00025-of-00061.safetensors",
|
|
|
|
|
250 |
"model.layers.32.self_attn.v_proj.weight": "model-00025-of-00061.safetensors",
|
251 |
"model.layers.33.input_layernorm.weight": "model-00026-of-00061.safetensors",
|
252 |
"model.layers.33.mlp.down_proj.weight": "model-00026-of-00061.safetensors",
|
|
|
255 |
"model.layers.33.post_attention_layernorm.weight": "model-00026-of-00061.safetensors",
|
256 |
"model.layers.33.self_attn.k_proj.weight": "model-00025-of-00061.safetensors",
|
257 |
"model.layers.33.self_attn.o_proj.weight": "model-00025-of-00061.safetensors",
|
|
|
|
|
258 |
"model.layers.33.self_attn.q_proj.weight": "model-00025-of-00061.safetensors",
|
|
|
|
|
259 |
"model.layers.33.self_attn.v_proj.weight": "model-00025-of-00061.safetensors",
|
260 |
"model.layers.34.input_layernorm.weight": "model-00027-of-00061.safetensors",
|
261 |
"model.layers.34.mlp.down_proj.weight": "model-00027-of-00061.safetensors",
|
|
|
264 |
"model.layers.34.post_attention_layernorm.weight": "model-00027-of-00061.safetensors",
|
265 |
"model.layers.34.self_attn.k_proj.weight": "model-00026-of-00061.safetensors",
|
266 |
"model.layers.34.self_attn.o_proj.weight": "model-00026-of-00061.safetensors",
|
|
|
|
|
267 |
"model.layers.34.self_attn.q_proj.weight": "model-00026-of-00061.safetensors",
|
|
|
|
|
268 |
"model.layers.34.self_attn.v_proj.weight": "model-00026-of-00061.safetensors",
|
269 |
"model.layers.35.input_layernorm.weight": "model-00028-of-00061.safetensors",
|
270 |
"model.layers.35.mlp.down_proj.weight": "model-00028-of-00061.safetensors",
|
|
|
273 |
"model.layers.35.post_attention_layernorm.weight": "model-00028-of-00061.safetensors",
|
274 |
"model.layers.35.self_attn.k_proj.weight": "model-00027-of-00061.safetensors",
|
275 |
"model.layers.35.self_attn.o_proj.weight": "model-00027-of-00061.safetensors",
|
|
|
|
|
276 |
"model.layers.35.self_attn.q_proj.weight": "model-00027-of-00061.safetensors",
|
|
|
|
|
277 |
"model.layers.35.self_attn.v_proj.weight": "model-00027-of-00061.safetensors",
|
278 |
"model.layers.36.input_layernorm.weight": "model-00028-of-00061.safetensors",
|
279 |
"model.layers.36.mlp.down_proj.weight": "model-00028-of-00061.safetensors",
|
|
|
282 |
"model.layers.36.post_attention_layernorm.weight": "model-00028-of-00061.safetensors",
|
283 |
"model.layers.36.self_attn.k_proj.weight": "model-00028-of-00061.safetensors",
|
284 |
"model.layers.36.self_attn.o_proj.weight": "model-00028-of-00061.safetensors",
|
|
|
|
|
285 |
"model.layers.36.self_attn.q_proj.weight": "model-00028-of-00061.safetensors",
|
|
|
|
|
286 |
"model.layers.36.self_attn.v_proj.weight": "model-00028-of-00061.safetensors",
|
287 |
"model.layers.37.input_layernorm.weight": "model-00029-of-00061.safetensors",
|
288 |
"model.layers.37.mlp.down_proj.weight": "model-00029-of-00061.safetensors",
|
|
|
291 |
"model.layers.37.post_attention_layernorm.weight": "model-00029-of-00061.safetensors",
|
292 |
"model.layers.37.self_attn.k_proj.weight": "model-00028-of-00061.safetensors",
|
293 |
"model.layers.37.self_attn.o_proj.weight": "model-00028-of-00061.safetensors",
|
|
|
|
|
294 |
"model.layers.37.self_attn.q_proj.weight": "model-00028-of-00061.safetensors",
|
|
|
|
|
295 |
"model.layers.37.self_attn.v_proj.weight": "model-00028-of-00061.safetensors",
|
296 |
"model.layers.38.input_layernorm.weight": "model-00030-of-00061.safetensors",
|
297 |
"model.layers.38.mlp.down_proj.weight": "model-00030-of-00061.safetensors",
|
|
|
300 |
"model.layers.38.post_attention_layernorm.weight": "model-00030-of-00061.safetensors",
|
301 |
"model.layers.38.self_attn.k_proj.weight": "model-00029-of-00061.safetensors",
|
302 |
"model.layers.38.self_attn.o_proj.weight": "model-00029-of-00061.safetensors",
|
|
|
|
|
303 |
"model.layers.38.self_attn.q_proj.weight": "model-00029-of-00061.safetensors",
|
|
|
|
|
304 |
"model.layers.38.self_attn.v_proj.weight": "model-00029-of-00061.safetensors",
|
305 |
"model.layers.39.input_layernorm.weight": "model-00031-of-00061.safetensors",
|
306 |
"model.layers.39.mlp.down_proj.weight": "model-00031-of-00061.safetensors",
|
|
|
309 |
"model.layers.39.post_attention_layernorm.weight": "model-00031-of-00061.safetensors",
|
310 |
"model.layers.39.self_attn.k_proj.weight": "model-00030-of-00061.safetensors",
|
311 |
"model.layers.39.self_attn.o_proj.weight": "model-00030-of-00061.safetensors",
|
|
|
|
|
312 |
"model.layers.39.self_attn.q_proj.weight": "model-00030-of-00061.safetensors",
|
|
|
|
|
313 |
"model.layers.39.self_attn.v_proj.weight": "model-00030-of-00061.safetensors",
|
314 |
"model.layers.4.input_layernorm.weight": "model-00004-of-00061.safetensors",
|
315 |
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00061.safetensors",
|
|
|
318 |
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00061.safetensors",
|
319 |
"model.layers.4.self_attn.k_proj.weight": "model-00004-of-00061.safetensors",
|
320 |
"model.layers.4.self_attn.o_proj.weight": "model-00004-of-00061.safetensors",
|
|
|
|
|
321 |
"model.layers.4.self_attn.q_proj.weight": "model-00004-of-00061.safetensors",
|
|
|
|
|
322 |
"model.layers.4.self_attn.v_proj.weight": "model-00004-of-00061.safetensors",
|
323 |
"model.layers.40.input_layernorm.weight": "model-00031-of-00061.safetensors",
|
324 |
"model.layers.40.mlp.down_proj.weight": "model-00031-of-00061.safetensors",
|
|
|
327 |
"model.layers.40.post_attention_layernorm.weight": "model-00031-of-00061.safetensors",
|
328 |
"model.layers.40.self_attn.k_proj.weight": "model-00031-of-00061.safetensors",
|
329 |
"model.layers.40.self_attn.o_proj.weight": "model-00031-of-00061.safetensors",
|
|
|
|
|
330 |
"model.layers.40.self_attn.q_proj.weight": "model-00031-of-00061.safetensors",
|
|
|
|
|
331 |
"model.layers.40.self_attn.v_proj.weight": "model-00031-of-00061.safetensors",
|
332 |
"model.layers.41.input_layernorm.weight": "model-00032-of-00061.safetensors",
|
333 |
"model.layers.41.mlp.down_proj.weight": "model-00032-of-00061.safetensors",
|
|
|
336 |
"model.layers.41.post_attention_layernorm.weight": "model-00032-of-00061.safetensors",
|
337 |
"model.layers.41.self_attn.k_proj.weight": "model-00031-of-00061.safetensors",
|
338 |
"model.layers.41.self_attn.o_proj.weight": "model-00031-of-00061.safetensors",
|
|
|
|
|
339 |
"model.layers.41.self_attn.q_proj.weight": "model-00031-of-00061.safetensors",
|
|
|
|
|
340 |
"model.layers.41.self_attn.v_proj.weight": "model-00031-of-00061.safetensors",
|
341 |
"model.layers.42.input_layernorm.weight": "model-00033-of-00061.safetensors",
|
342 |
"model.layers.42.mlp.down_proj.weight": "model-00033-of-00061.safetensors",
|
|
|
345 |
"model.layers.42.post_attention_layernorm.weight": "model-00033-of-00061.safetensors",
|
346 |
"model.layers.42.self_attn.k_proj.weight": "model-00032-of-00061.safetensors",
|
347 |
"model.layers.42.self_attn.o_proj.weight": "model-00032-of-00061.safetensors",
|
|
|
|
|
348 |
"model.layers.42.self_attn.q_proj.weight": "model-00032-of-00061.safetensors",
|
|
|
|
|
349 |
"model.layers.42.self_attn.v_proj.weight": "model-00032-of-00061.safetensors",
|
350 |
"model.layers.43.input_layernorm.weight": "model-00034-of-00061.safetensors",
|
351 |
"model.layers.43.mlp.down_proj.weight": "model-00034-of-00061.safetensors",
|
|
|
354 |
"model.layers.43.post_attention_layernorm.weight": "model-00034-of-00061.safetensors",
|
355 |
"model.layers.43.self_attn.k_proj.weight": "model-00033-of-00061.safetensors",
|
356 |
"model.layers.43.self_attn.o_proj.weight": "model-00033-of-00061.safetensors",
|
|
|
|
|
357 |
"model.layers.43.self_attn.q_proj.weight": "model-00033-of-00061.safetensors",
|
|
|
|
|
358 |
"model.layers.43.self_attn.v_proj.weight": "model-00033-of-00061.safetensors",
|
359 |
"model.layers.44.input_layernorm.weight": "model-00034-of-00061.safetensors",
|
360 |
"model.layers.44.mlp.down_proj.weight": "model-00034-of-00061.safetensors",
|
|
|
363 |
"model.layers.44.post_attention_layernorm.weight": "model-00034-of-00061.safetensors",
|
364 |
"model.layers.44.self_attn.k_proj.weight": "model-00034-of-00061.safetensors",
|
365 |
"model.layers.44.self_attn.o_proj.weight": "model-00034-of-00061.safetensors",
|
|
|
|
|
366 |
"model.layers.44.self_attn.q_proj.weight": "model-00034-of-00061.safetensors",
|
|
|
|
|
367 |
"model.layers.44.self_attn.v_proj.weight": "model-00034-of-00061.safetensors",
|
368 |
"model.layers.45.input_layernorm.weight": "model-00035-of-00061.safetensors",
|
369 |
"model.layers.45.mlp.down_proj.weight": "model-00035-of-00061.safetensors",
|
|
|
372 |
"model.layers.45.post_attention_layernorm.weight": "model-00035-of-00061.safetensors",
|
373 |
"model.layers.45.self_attn.k_proj.weight": "model-00034-of-00061.safetensors",
|
374 |
"model.layers.45.self_attn.o_proj.weight": "model-00034-of-00061.safetensors",
|
|
|
|
|
375 |
"model.layers.45.self_attn.q_proj.weight": "model-00034-of-00061.safetensors",
|
|
|
|
|
376 |
"model.layers.45.self_attn.v_proj.weight": "model-00034-of-00061.safetensors",
|
377 |
"model.layers.46.input_layernorm.weight": "model-00036-of-00061.safetensors",
|
378 |
"model.layers.46.mlp.down_proj.weight": "model-00036-of-00061.safetensors",
|
|
|
381 |
"model.layers.46.post_attention_layernorm.weight": "model-00036-of-00061.safetensors",
|
382 |
"model.layers.46.self_attn.k_proj.weight": "model-00035-of-00061.safetensors",
|
383 |
"model.layers.46.self_attn.o_proj.weight": "model-00035-of-00061.safetensors",
|
|
|
|
|
384 |
"model.layers.46.self_attn.q_proj.weight": "model-00035-of-00061.safetensors",
|
|
|
|
|
385 |
"model.layers.46.self_attn.v_proj.weight": "model-00035-of-00061.safetensors",
|
386 |
"model.layers.47.input_layernorm.weight": "model-00037-of-00061.safetensors",
|
387 |
"model.layers.47.mlp.down_proj.weight": "model-00037-of-00061.safetensors",
|
|
|
390 |
"model.layers.47.post_attention_layernorm.weight": "model-00037-of-00061.safetensors",
|
391 |
"model.layers.47.self_attn.k_proj.weight": "model-00036-of-00061.safetensors",
|
392 |
"model.layers.47.self_attn.o_proj.weight": "model-00036-of-00061.safetensors",
|
|
|
|
|
393 |
"model.layers.47.self_attn.q_proj.weight": "model-00036-of-00061.safetensors",
|
|
|
|
|
394 |
"model.layers.47.self_attn.v_proj.weight": "model-00036-of-00061.safetensors",
|
395 |
"model.layers.48.input_layernorm.weight": "model-00037-of-00061.safetensors",
|
396 |
"model.layers.48.mlp.down_proj.weight": "model-00037-of-00061.safetensors",
|
|
|
399 |
"model.layers.48.post_attention_layernorm.weight": "model-00037-of-00061.safetensors",
|
400 |
"model.layers.48.self_attn.k_proj.weight": "model-00037-of-00061.safetensors",
|
401 |
"model.layers.48.self_attn.o_proj.weight": "model-00037-of-00061.safetensors",
|
|
|
|
|
402 |
"model.layers.48.self_attn.q_proj.weight": "model-00037-of-00061.safetensors",
|
|
|
|
|
403 |
"model.layers.48.self_attn.v_proj.weight": "model-00037-of-00061.safetensors",
|
404 |
"model.layers.49.input_layernorm.weight": "model-00038-of-00061.safetensors",
|
405 |
"model.layers.49.mlp.down_proj.weight": "model-00038-of-00061.safetensors",
|
|
|
408 |
"model.layers.49.post_attention_layernorm.weight": "model-00038-of-00061.safetensors",
|
409 |
"model.layers.49.self_attn.k_proj.weight": "model-00037-of-00061.safetensors",
|
410 |
"model.layers.49.self_attn.o_proj.weight": "model-00037-of-00061.safetensors",
|
|
|
|
|
411 |
"model.layers.49.self_attn.q_proj.weight": "model-00037-of-00061.safetensors",
|
|
|
|
|
412 |
"model.layers.49.self_attn.v_proj.weight": "model-00037-of-00061.safetensors",
|
413 |
"model.layers.5.input_layernorm.weight": "model-00005-of-00061.safetensors",
|
414 |
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00061.safetensors",
|
|
|
417 |
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00061.safetensors",
|
418 |
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00061.safetensors",
|
419 |
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00061.safetensors",
|
|
|
|
|
420 |
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00061.safetensors",
|
|
|
|
|
421 |
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00061.safetensors",
|
422 |
"model.layers.50.input_layernorm.weight": "model-00039-of-00061.safetensors",
|
423 |
"model.layers.50.mlp.down_proj.weight": "model-00039-of-00061.safetensors",
|
|
|
426 |
"model.layers.50.post_attention_layernorm.weight": "model-00039-of-00061.safetensors",
|
427 |
"model.layers.50.self_attn.k_proj.weight": "model-00038-of-00061.safetensors",
|
428 |
"model.layers.50.self_attn.o_proj.weight": "model-00038-of-00061.safetensors",
|
|
|
|
|
429 |
"model.layers.50.self_attn.q_proj.weight": "model-00038-of-00061.safetensors",
|
|
|
|
|
430 |
"model.layers.50.self_attn.v_proj.weight": "model-00038-of-00061.safetensors",
|
431 |
"model.layers.51.input_layernorm.weight": "model-00040-of-00061.safetensors",
|
432 |
"model.layers.51.mlp.down_proj.weight": "model-00040-of-00061.safetensors",
|
|
|
435 |
"model.layers.51.post_attention_layernorm.weight": "model-00040-of-00061.safetensors",
|
436 |
"model.layers.51.self_attn.k_proj.weight": "model-00039-of-00061.safetensors",
|
437 |
"model.layers.51.self_attn.o_proj.weight": "model-00039-of-00061.safetensors",
|
|
|
|
|
438 |
"model.layers.51.self_attn.q_proj.weight": "model-00039-of-00061.safetensors",
|
|
|
|
|
439 |
"model.layers.51.self_attn.v_proj.weight": "model-00039-of-00061.safetensors",
|
440 |
"model.layers.52.input_layernorm.weight": "model-00040-of-00061.safetensors",
|
441 |
"model.layers.52.mlp.down_proj.weight": "model-00040-of-00061.safetensors",
|
|
|
444 |
"model.layers.52.post_attention_layernorm.weight": "model-00040-of-00061.safetensors",
|
445 |
"model.layers.52.self_attn.k_proj.weight": "model-00040-of-00061.safetensors",
|
446 |
"model.layers.52.self_attn.o_proj.weight": "model-00040-of-00061.safetensors",
|
|
|
|
|
447 |
"model.layers.52.self_attn.q_proj.weight": "model-00040-of-00061.safetensors",
|
|
|
|
|
448 |
"model.layers.52.self_attn.v_proj.weight": "model-00040-of-00061.safetensors",
|
449 |
"model.layers.53.input_layernorm.weight": "model-00041-of-00061.safetensors",
|
450 |
"model.layers.53.mlp.down_proj.weight": "model-00041-of-00061.safetensors",
|
|
|
453 |
"model.layers.53.post_attention_layernorm.weight": "model-00041-of-00061.safetensors",
|
454 |
"model.layers.53.self_attn.k_proj.weight": "model-00040-of-00061.safetensors",
|
455 |
"model.layers.53.self_attn.o_proj.weight": "model-00040-of-00061.safetensors",
|
|
|
|
|
456 |
"model.layers.53.self_attn.q_proj.weight": "model-00040-of-00061.safetensors",
|
|
|
|
|
457 |
"model.layers.53.self_attn.v_proj.weight": "model-00040-of-00061.safetensors",
|
458 |
"model.layers.54.input_layernorm.weight": "model-00042-of-00061.safetensors",
|
459 |
"model.layers.54.mlp.down_proj.weight": "model-00042-of-00061.safetensors",
|
|
|
462 |
"model.layers.54.post_attention_layernorm.weight": "model-00042-of-00061.safetensors",
|
463 |
"model.layers.54.self_attn.k_proj.weight": "model-00041-of-00061.safetensors",
|
464 |
"model.layers.54.self_attn.o_proj.weight": "model-00041-of-00061.safetensors",
|
|
|
|
|
465 |
"model.layers.54.self_attn.q_proj.weight": "model-00041-of-00061.safetensors",
|
|
|
|
|
466 |
"model.layers.54.self_attn.v_proj.weight": "model-00041-of-00061.safetensors",
|
467 |
"model.layers.55.input_layernorm.weight": "model-00043-of-00061.safetensors",
|
468 |
"model.layers.55.mlp.down_proj.weight": "model-00043-of-00061.safetensors",
|
|
|
471 |
"model.layers.55.post_attention_layernorm.weight": "model-00043-of-00061.safetensors",
|
472 |
"model.layers.55.self_attn.k_proj.weight": "model-00042-of-00061.safetensors",
|
473 |
"model.layers.55.self_attn.o_proj.weight": "model-00042-of-00061.safetensors",
|
|
|
|
|
474 |
"model.layers.55.self_attn.q_proj.weight": "model-00042-of-00061.safetensors",
|
|
|
|
|
475 |
"model.layers.55.self_attn.v_proj.weight": "model-00042-of-00061.safetensors",
|
476 |
"model.layers.56.input_layernorm.weight": "model-00043-of-00061.safetensors",
|
477 |
"model.layers.56.mlp.down_proj.weight": "model-00043-of-00061.safetensors",
|
|
|
480 |
"model.layers.56.post_attention_layernorm.weight": "model-00043-of-00061.safetensors",
|
481 |
"model.layers.56.self_attn.k_proj.weight": "model-00043-of-00061.safetensors",
|
482 |
"model.layers.56.self_attn.o_proj.weight": "model-00043-of-00061.safetensors",
|
|
|
|
|
483 |
"model.layers.56.self_attn.q_proj.weight": "model-00043-of-00061.safetensors",
|
|
|
|
|
484 |
"model.layers.56.self_attn.v_proj.weight": "model-00043-of-00061.safetensors",
|
485 |
"model.layers.57.input_layernorm.weight": "model-00044-of-00061.safetensors",
|
486 |
"model.layers.57.mlp.down_proj.weight": "model-00044-of-00061.safetensors",
|
|
|
489 |
"model.layers.57.post_attention_layernorm.weight": "model-00044-of-00061.safetensors",
|
490 |
"model.layers.57.self_attn.k_proj.weight": "model-00043-of-00061.safetensors",
|
491 |
"model.layers.57.self_attn.o_proj.weight": "model-00043-of-00061.safetensors",
|
|
|
|
|
492 |
"model.layers.57.self_attn.q_proj.weight": "model-00043-of-00061.safetensors",
|
|
|
|
|
493 |
"model.layers.57.self_attn.v_proj.weight": "model-00043-of-00061.safetensors",
|
494 |
"model.layers.58.input_layernorm.weight": "model-00045-of-00061.safetensors",
|
495 |
"model.layers.58.mlp.down_proj.weight": "model-00045-of-00061.safetensors",
|
|
|
498 |
"model.layers.58.post_attention_layernorm.weight": "model-00045-of-00061.safetensors",
|
499 |
"model.layers.58.self_attn.k_proj.weight": "model-00044-of-00061.safetensors",
|
500 |
"model.layers.58.self_attn.o_proj.weight": "model-00044-of-00061.safetensors",
|
|
|
|
|
501 |
"model.layers.58.self_attn.q_proj.weight": "model-00044-of-00061.safetensors",
|
|
|
|
|
502 |
"model.layers.58.self_attn.v_proj.weight": "model-00044-of-00061.safetensors",
|
503 |
"model.layers.59.input_layernorm.weight": "model-00046-of-00061.safetensors",
|
504 |
"model.layers.59.mlp.down_proj.weight": "model-00046-of-00061.safetensors",
|
|
|
507 |
"model.layers.59.post_attention_layernorm.weight": "model-00046-of-00061.safetensors",
|
508 |
"model.layers.59.self_attn.k_proj.weight": "model-00045-of-00061.safetensors",
|
509 |
"model.layers.59.self_attn.o_proj.weight": "model-00045-of-00061.safetensors",
|
|
|
|
|
510 |
"model.layers.59.self_attn.q_proj.weight": "model-00045-of-00061.safetensors",
|
|
|
|
|
511 |
"model.layers.59.self_attn.v_proj.weight": "model-00045-of-00061.safetensors",
|
512 |
"model.layers.6.input_layernorm.weight": "model-00006-of-00061.safetensors",
|
513 |
"model.layers.6.mlp.down_proj.weight": "model-00006-of-00061.safetensors",
|
|
|
516 |
"model.layers.6.post_attention_layernorm.weight": "model-00006-of-00061.safetensors",
|
517 |
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00061.safetensors",
|
518 |
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00061.safetensors",
|
|
|
|
|
519 |
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00061.safetensors",
|
|
|
|
|
520 |
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00061.safetensors",
|
521 |
"model.layers.60.input_layernorm.weight": "model-00046-of-00061.safetensors",
|
522 |
"model.layers.60.mlp.down_proj.weight": "model-00046-of-00061.safetensors",
|
|
|
525 |
"model.layers.60.post_attention_layernorm.weight": "model-00046-of-00061.safetensors",
|
526 |
"model.layers.60.self_attn.k_proj.weight": "model-00046-of-00061.safetensors",
|
527 |
"model.layers.60.self_attn.o_proj.weight": "model-00046-of-00061.safetensors",
|
|
|
|
|
528 |
"model.layers.60.self_attn.q_proj.weight": "model-00046-of-00061.safetensors",
|
|
|
|
|
529 |
"model.layers.60.self_attn.v_proj.weight": "model-00046-of-00061.safetensors",
|
530 |
"model.layers.61.input_layernorm.weight": "model-00047-of-00061.safetensors",
|
531 |
"model.layers.61.mlp.down_proj.weight": "model-00047-of-00061.safetensors",
|
|
|
534 |
"model.layers.61.post_attention_layernorm.weight": "model-00047-of-00061.safetensors",
|
535 |
"model.layers.61.self_attn.k_proj.weight": "model-00046-of-00061.safetensors",
|
536 |
"model.layers.61.self_attn.o_proj.weight": "model-00046-of-00061.safetensors",
|
|
|
|
|
537 |
"model.layers.61.self_attn.q_proj.weight": "model-00046-of-00061.safetensors",
|
|
|
|
|
538 |
"model.layers.61.self_attn.v_proj.weight": "model-00046-of-00061.safetensors",
|
539 |
"model.layers.62.input_layernorm.weight": "model-00048-of-00061.safetensors",
|
540 |
"model.layers.62.mlp.down_proj.weight": "model-00048-of-00061.safetensors",
|
|
|
543 |
"model.layers.62.post_attention_layernorm.weight": "model-00048-of-00061.safetensors",
|
544 |
"model.layers.62.self_attn.k_proj.weight": "model-00047-of-00061.safetensors",
|
545 |
"model.layers.62.self_attn.o_proj.weight": "model-00047-of-00061.safetensors",
|
|
|
|
|
546 |
"model.layers.62.self_attn.q_proj.weight": "model-00047-of-00061.safetensors",
|
|
|
|
|
547 |
"model.layers.62.self_attn.v_proj.weight": "model-00047-of-00061.safetensors",
|
548 |
"model.layers.63.input_layernorm.weight": "model-00049-of-00061.safetensors",
|
549 |
"model.layers.63.mlp.down_proj.weight": "model-00049-of-00061.safetensors",
|
|
|
552 |
"model.layers.63.post_attention_layernorm.weight": "model-00049-of-00061.safetensors",
|
553 |
"model.layers.63.self_attn.k_proj.weight": "model-00048-of-00061.safetensors",
|
554 |
"model.layers.63.self_attn.o_proj.weight": "model-00048-of-00061.safetensors",
|
|
|
|
|
555 |
"model.layers.63.self_attn.q_proj.weight": "model-00048-of-00061.safetensors",
|
|
|
|
|
556 |
"model.layers.63.self_attn.v_proj.weight": "model-00048-of-00061.safetensors",
|
557 |
"model.layers.64.input_layernorm.weight": "model-00049-of-00061.safetensors",
|
558 |
"model.layers.64.mlp.down_proj.weight": "model-00049-of-00061.safetensors",
|
|
|
561 |
"model.layers.64.post_attention_layernorm.weight": "model-00049-of-00061.safetensors",
|
562 |
"model.layers.64.self_attn.k_proj.weight": "model-00049-of-00061.safetensors",
|
563 |
"model.layers.64.self_attn.o_proj.weight": "model-00049-of-00061.safetensors",
|
|
|
|
|
564 |
"model.layers.64.self_attn.q_proj.weight": "model-00049-of-00061.safetensors",
|
|
|
|
|
565 |
"model.layers.64.self_attn.v_proj.weight": "model-00049-of-00061.safetensors",
|
566 |
"model.layers.65.input_layernorm.weight": "model-00050-of-00061.safetensors",
|
567 |
"model.layers.65.mlp.down_proj.weight": "model-00050-of-00061.safetensors",
|
|
|
570 |
"model.layers.65.post_attention_layernorm.weight": "model-00050-of-00061.safetensors",
|
571 |
"model.layers.65.self_attn.k_proj.weight": "model-00049-of-00061.safetensors",
|
572 |
"model.layers.65.self_attn.o_proj.weight": "model-00049-of-00061.safetensors",
|
|
|
|
|
573 |
"model.layers.65.self_attn.q_proj.weight": "model-00049-of-00061.safetensors",
|
|
|
|
|
574 |
"model.layers.65.self_attn.v_proj.weight": "model-00049-of-00061.safetensors",
|
575 |
"model.layers.66.input_layernorm.weight": "model-00051-of-00061.safetensors",
|
576 |
"model.layers.66.mlp.down_proj.weight": "model-00051-of-00061.safetensors",
|
|
|
579 |
"model.layers.66.post_attention_layernorm.weight": "model-00051-of-00061.safetensors",
|
580 |
"model.layers.66.self_attn.k_proj.weight": "model-00050-of-00061.safetensors",
|
581 |
"model.layers.66.self_attn.o_proj.weight": "model-00050-of-00061.safetensors",
|
|
|
|
|
582 |
"model.layers.66.self_attn.q_proj.weight": "model-00050-of-00061.safetensors",
|
|
|
|
|
583 |
"model.layers.66.self_attn.v_proj.weight": "model-00050-of-00061.safetensors",
|
584 |
"model.layers.67.input_layernorm.weight": "model-00052-of-00061.safetensors",
|
585 |
"model.layers.67.mlp.down_proj.weight": "model-00052-of-00061.safetensors",
|
|
|
588 |
"model.layers.67.post_attention_layernorm.weight": "model-00052-of-00061.safetensors",
|
589 |
"model.layers.67.self_attn.k_proj.weight": "model-00051-of-00061.safetensors",
|
590 |
"model.layers.67.self_attn.o_proj.weight": "model-00051-of-00061.safetensors",
|
|
|
|
|
591 |
"model.layers.67.self_attn.q_proj.weight": "model-00051-of-00061.safetensors",
|
|
|
|
|
592 |
"model.layers.67.self_attn.v_proj.weight": "model-00051-of-00061.safetensors",
|
593 |
"model.layers.68.input_layernorm.weight": "model-00052-of-00061.safetensors",
|
594 |
"model.layers.68.mlp.down_proj.weight": "model-00052-of-00061.safetensors",
|
|
|
597 |
"model.layers.68.post_attention_layernorm.weight": "model-00052-of-00061.safetensors",
|
598 |
"model.layers.68.self_attn.k_proj.weight": "model-00052-of-00061.safetensors",
|
599 |
"model.layers.68.self_attn.o_proj.weight": "model-00052-of-00061.safetensors",
|
|
|
|
|
600 |
"model.layers.68.self_attn.q_proj.weight": "model-00052-of-00061.safetensors",
|
|
|
|
|
601 |
"model.layers.68.self_attn.v_proj.weight": "model-00052-of-00061.safetensors",
|
602 |
"model.layers.69.input_layernorm.weight": "model-00053-of-00061.safetensors",
|
603 |
"model.layers.69.mlp.down_proj.weight": "model-00053-of-00061.safetensors",
|
|
|
606 |
"model.layers.69.post_attention_layernorm.weight": "model-00053-of-00061.safetensors",
|
607 |
"model.layers.69.self_attn.k_proj.weight": "model-00052-of-00061.safetensors",
|
608 |
"model.layers.69.self_attn.o_proj.weight": "model-00052-of-00061.safetensors",
|
|
|
|
|
609 |
"model.layers.69.self_attn.q_proj.weight": "model-00052-of-00061.safetensors",
|
|
|
|
|
610 |
"model.layers.69.self_attn.v_proj.weight": "model-00052-of-00061.safetensors",
|
611 |
"model.layers.7.input_layernorm.weight": "model-00007-of-00061.safetensors",
|
612 |
"model.layers.7.mlp.down_proj.weight": "model-00007-of-00061.safetensors",
|
|
|
615 |
"model.layers.7.post_attention_layernorm.weight": "model-00007-of-00061.safetensors",
|
616 |
"model.layers.7.self_attn.k_proj.weight": "model-00006-of-00061.safetensors",
|
617 |
"model.layers.7.self_attn.o_proj.weight": "model-00006-of-00061.safetensors",
|
|
|
|
|
618 |
"model.layers.7.self_attn.q_proj.weight": "model-00006-of-00061.safetensors",
|
|
|
|
|
619 |
"model.layers.7.self_attn.v_proj.weight": "model-00006-of-00061.safetensors",
|
620 |
"model.layers.70.input_layernorm.weight": "model-00054-of-00061.safetensors",
|
621 |
"model.layers.70.mlp.down_proj.weight": "model-00054-of-00061.safetensors",
|
|
|
624 |
"model.layers.70.post_attention_layernorm.weight": "model-00054-of-00061.safetensors",
|
625 |
"model.layers.70.self_attn.k_proj.weight": "model-00053-of-00061.safetensors",
|
626 |
"model.layers.70.self_attn.o_proj.weight": "model-00053-of-00061.safetensors",
|
|
|
|
|
627 |
"model.layers.70.self_attn.q_proj.weight": "model-00053-of-00061.safetensors",
|
|
|
|
|
628 |
"model.layers.70.self_attn.v_proj.weight": "model-00053-of-00061.safetensors",
|
629 |
"model.layers.71.input_layernorm.weight": "model-00055-of-00061.safetensors",
|
630 |
"model.layers.71.mlp.down_proj.weight": "model-00055-of-00061.safetensors",
|
|
|
633 |
"model.layers.71.post_attention_layernorm.weight": "model-00055-of-00061.safetensors",
|
634 |
"model.layers.71.self_attn.k_proj.weight": "model-00054-of-00061.safetensors",
|
635 |
"model.layers.71.self_attn.o_proj.weight": "model-00054-of-00061.safetensors",
|
|
|
|
|
636 |
"model.layers.71.self_attn.q_proj.weight": "model-00054-of-00061.safetensors",
|
|
|
|
|
637 |
"model.layers.71.self_attn.v_proj.weight": "model-00054-of-00061.safetensors",
|
638 |
"model.layers.72.input_layernorm.weight": "model-00055-of-00061.safetensors",
|
639 |
"model.layers.72.mlp.down_proj.weight": "model-00055-of-00061.safetensors",
|
|
|
642 |
"model.layers.72.post_attention_layernorm.weight": "model-00055-of-00061.safetensors",
|
643 |
"model.layers.72.self_attn.k_proj.weight": "model-00055-of-00061.safetensors",
|
644 |
"model.layers.72.self_attn.o_proj.weight": "model-00055-of-00061.safetensors",
|
|
|
|
|
645 |
"model.layers.72.self_attn.q_proj.weight": "model-00055-of-00061.safetensors",
|
|
|
|
|
646 |
"model.layers.72.self_attn.v_proj.weight": "model-00055-of-00061.safetensors",
|
647 |
"model.layers.73.input_layernorm.weight": "model-00056-of-00061.safetensors",
|
648 |
"model.layers.73.mlp.down_proj.weight": "model-00056-of-00061.safetensors",
|
|
|
651 |
"model.layers.73.post_attention_layernorm.weight": "model-00056-of-00061.safetensors",
|
652 |
"model.layers.73.self_attn.k_proj.weight": "model-00055-of-00061.safetensors",
|
653 |
"model.layers.73.self_attn.o_proj.weight": "model-00055-of-00061.safetensors",
|
|
|
|
|
654 |
"model.layers.73.self_attn.q_proj.weight": "model-00055-of-00061.safetensors",
|
|
|
|
|
655 |
"model.layers.73.self_attn.v_proj.weight": "model-00055-of-00061.safetensors",
|
656 |
"model.layers.74.input_layernorm.weight": "model-00057-of-00061.safetensors",
|
657 |
"model.layers.74.mlp.down_proj.weight": "model-00057-of-00061.safetensors",
|
|
|
660 |
"model.layers.74.post_attention_layernorm.weight": "model-00057-of-00061.safetensors",
|
661 |
"model.layers.74.self_attn.k_proj.weight": "model-00056-of-00061.safetensors",
|
662 |
"model.layers.74.self_attn.o_proj.weight": "model-00056-of-00061.safetensors",
|
|
|
|
|
663 |
"model.layers.74.self_attn.q_proj.weight": "model-00056-of-00061.safetensors",
|
|
|
|
|
664 |
"model.layers.74.self_attn.v_proj.weight": "model-00056-of-00061.safetensors",
|
665 |
"model.layers.75.input_layernorm.weight": "model-00058-of-00061.safetensors",
|
666 |
"model.layers.75.mlp.down_proj.weight": "model-00058-of-00061.safetensors",
|
|
|
669 |
"model.layers.75.post_attention_layernorm.weight": "model-00058-of-00061.safetensors",
|
670 |
"model.layers.75.self_attn.k_proj.weight": "model-00057-of-00061.safetensors",
|
671 |
"model.layers.75.self_attn.o_proj.weight": "model-00057-of-00061.safetensors",
|
|
|
|
|
672 |
"model.layers.75.self_attn.q_proj.weight": "model-00057-of-00061.safetensors",
|
|
|
|
|
673 |
"model.layers.75.self_attn.v_proj.weight": "model-00057-of-00061.safetensors",
|
674 |
"model.layers.76.input_layernorm.weight": "model-00058-of-00061.safetensors",
|
675 |
"model.layers.76.mlp.down_proj.weight": "model-00058-of-00061.safetensors",
|
|
|
678 |
"model.layers.76.post_attention_layernorm.weight": "model-00058-of-00061.safetensors",
|
679 |
"model.layers.76.self_attn.k_proj.weight": "model-00058-of-00061.safetensors",
|
680 |
"model.layers.76.self_attn.o_proj.weight": "model-00058-of-00061.safetensors",
|
|
|
|
|
681 |
"model.layers.76.self_attn.q_proj.weight": "model-00058-of-00061.safetensors",
|
|
|
|
|
682 |
"model.layers.76.self_attn.v_proj.weight": "model-00058-of-00061.safetensors",
|
683 |
"model.layers.77.input_layernorm.weight": "model-00059-of-00061.safetensors",
|
684 |
"model.layers.77.mlp.down_proj.weight": "model-00059-of-00061.safetensors",
|
|
|
687 |
"model.layers.77.post_attention_layernorm.weight": "model-00059-of-00061.safetensors",
|
688 |
"model.layers.77.self_attn.k_proj.weight": "model-00058-of-00061.safetensors",
|
689 |
"model.layers.77.self_attn.o_proj.weight": "model-00058-of-00061.safetensors",
|
|
|
|
|
690 |
"model.layers.77.self_attn.q_proj.weight": "model-00058-of-00061.safetensors",
|
|
|
|
|
691 |
"model.layers.77.self_attn.v_proj.weight": "model-00058-of-00061.safetensors",
|
692 |
"model.layers.78.input_layernorm.weight": "model-00060-of-00061.safetensors",
|
693 |
"model.layers.78.mlp.down_proj.weight": "model-00060-of-00061.safetensors",
|
|
|
696 |
"model.layers.78.post_attention_layernorm.weight": "model-00060-of-00061.safetensors",
|
697 |
"model.layers.78.self_attn.k_proj.weight": "model-00059-of-00061.safetensors",
|
698 |
"model.layers.78.self_attn.o_proj.weight": "model-00059-of-00061.safetensors",
|
|
|
|
|
699 |
"model.layers.78.self_attn.q_proj.weight": "model-00059-of-00061.safetensors",
|
|
|
|
|
700 |
"model.layers.78.self_attn.v_proj.weight": "model-00059-of-00061.safetensors",
|
701 |
"model.layers.79.input_layernorm.weight": "model-00061-of-00061.safetensors",
|
702 |
"model.layers.79.mlp.down_proj.weight": "model-00061-of-00061.safetensors",
|
|
|
705 |
"model.layers.79.post_attention_layernorm.weight": "model-00061-of-00061.safetensors",
|
706 |
"model.layers.79.self_attn.k_proj.weight": "model-00060-of-00061.safetensors",
|
707 |
"model.layers.79.self_attn.o_proj.weight": "model-00060-of-00061.safetensors",
|
|
|
|
|
708 |
"model.layers.79.self_attn.q_proj.weight": "model-00060-of-00061.safetensors",
|
|
|
|
|
709 |
"model.layers.79.self_attn.v_proj.weight": "model-00060-of-00061.safetensors",
|
710 |
"model.layers.8.input_layernorm.weight": "model-00007-of-00061.safetensors",
|
711 |
"model.layers.8.mlp.down_proj.weight": "model-00007-of-00061.safetensors",
|
|
|
714 |
"model.layers.8.post_attention_layernorm.weight": "model-00007-of-00061.safetensors",
|
715 |
"model.layers.8.self_attn.k_proj.weight": "model-00007-of-00061.safetensors",
|
716 |
"model.layers.8.self_attn.o_proj.weight": "model-00007-of-00061.safetensors",
|
|
|
|
|
717 |
"model.layers.8.self_attn.q_proj.weight": "model-00007-of-00061.safetensors",
|
|
|
|
|
718 |
"model.layers.8.self_attn.v_proj.weight": "model-00007-of-00061.safetensors",
|
719 |
"model.layers.9.input_layernorm.weight": "model-00008-of-00061.safetensors",
|
720 |
"model.layers.9.mlp.down_proj.weight": "model-00008-of-00061.safetensors",
|
|
|
723 |
"model.layers.9.post_attention_layernorm.weight": "model-00008-of-00061.safetensors",
|
724 |
"model.layers.9.self_attn.k_proj.weight": "model-00007-of-00061.safetensors",
|
725 |
"model.layers.9.self_attn.o_proj.weight": "model-00007-of-00061.safetensors",
|
|
|
|
|
726 |
"model.layers.9.self_attn.q_proj.weight": "model-00007-of-00061.safetensors",
|
|
|
|
|
727 |
"model.layers.9.self_attn.v_proj.weight": "model-00007-of-00061.safetensors",
|
728 |
"model.norm.weight": "model-00061-of-00061.safetensors"
|
729 |
}
|
special_tokens_map.json
CHANGED
@@ -1,11 +1,24 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"<
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
"pad_token": "</s>",
|
10 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
}
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -25,24 +27,14 @@
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
-
"additional_special_tokens": [
|
29 |
-
"<unk>",
|
30 |
-
"<s>",
|
31 |
-
"</s>"
|
32 |
-
],
|
33 |
"bos_token": "<s>",
|
34 |
"clean_up_tokenization_spaces": false,
|
35 |
"eos_token": "</s>",
|
36 |
"legacy": false,
|
37 |
-
"max_length": 2048,
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
39 |
"pad_token": "</s>",
|
40 |
-
"padding_side": "right",
|
41 |
"sp_model_kwargs": {},
|
42 |
-
"stride": 0,
|
43 |
"tokenizer_class": "LlamaTokenizer",
|
44 |
-
"truncation_side": "right",
|
45 |
-
"truncation_strategy": "longest_first",
|
46 |
"unk_token": "<unk>",
|
47 |
"use_default_system_prompt": true
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
|
|
|
|
|
|
|
|
|
|
30 |
"bos_token": "<s>",
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
|
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
"pad_token": "</s>",
|
|
|
36 |
"sp_model_kwargs": {},
|
|
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
38 |
"unk_token": "<unk>",
|
39 |
"use_default_system_prompt": true
|
40 |
}
|