Commit
•
3821d00
1
Parent(s):
f7aedad
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- DaringLotusLogo.png +3 -0
- README.md +15 -0
- config.json +28 -0
- mergekit_config.yml +19 -0
- model.safetensors.index.json +1 -0
- output.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
DaringLotusLogo.png filter=lfs diff=lfs merge=lfs -text
|
DaringLotusLogo.png
ADDED
![]() |
Git LFS Details
|
README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- Solar
|
5 |
+
- Mistral
|
6 |
+
- Roleplay
|
7 |
+
---
|
8 |
+
|
9 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64bb1109aaccfd28b023bcec/bjOB_8BsqVteKKxARPc13.png)
|
10 |
+
|
11 |
+
I managed to do a heavy density DARE TIES merge of SnowLotus and it's parent models (unusual strategy I know) that seems okay (prose not too bad, not incoherent). Early impressions are that this has slightly different prose - maybe a touch more GPT in there, as it talks of connections, but not at all to the degree that many more synthetically based models do. You probably will find that unobtrusive. Like it's sister model it can and does take lore, character cards and in context chat at times and creates with it, and is very descriptive. I cannot tell which is more coherent - occasionally they both get confused (as is typical with smaller models particularly onces with better prose). I did notice that when in particular contexts, SnowLotus' tendancy for exagerated excalation seemed stronger with this model. So there are differences (some prose and tone differences at least), and testin will probably tell which you prefer.
|
12 |
+
|
13 |
+
They share more in common that they do differences - descriptive, fairly creative, occassionally confused but also sometimes surprisingly bright. And the prose has lots of similarities too, it's not generally your 'light, lyrical and poetic' affair.
|
14 |
+
|
15 |
+
Summary at least so far, is this one is _slightly_ more gptish in prose and more inclined to escalate scenarios and descriptions in a sort of enthusiastic manner. Both do feed a lot off context, so if you give them stuff they should not be mild or timid.
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./SOLAR",
|
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": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 48,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.36.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: ./Frostwind
|
3 |
+
parameters:
|
4 |
+
density: [0.4] # density gradient
|
5 |
+
weight: 0.2
|
6 |
+
- model: ./Frostmaid
|
7 |
+
parameters:
|
8 |
+
density: [0.4] # density gradient
|
9 |
+
weight: 0.2
|
10 |
+
- model: ./SnowLotus-10.7B
|
11 |
+
parameters:
|
12 |
+
density: [0.96] # density gradient
|
13 |
+
weight: 0.9
|
14 |
+
merge_method: ties
|
15 |
+
base_model: ./SOLAR
|
16 |
+
parameters:
|
17 |
+
normalize: true
|
18 |
+
int8_mask: true
|
19 |
+
dtype: float16
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:964cd4ccb3a5dc114cc0884b85cd654c18bba4fb0e705afb268d5fac73e04b83
|
3 |
+
size 8226281044
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
42 |
+
}
|