初始化项目，由ModelHub XC社区提供模型
Model: Naphula/Goetia-24B-v1.3 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
Goetia_Map_v1.3.png filter=lfs diff=lfs merge=lfs -text
|
||||
3
Goetia_Map_v1.3.png
Normal file
3
Goetia_Map_v1.3.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:999ffea2ef0d75a47dc9d10a970f7f167abd2818f2d23da896948ba985ca99bb
|
||||
size 106919
|
||||
294
README.md
Normal file
294
README.md
Normal file
@@ -0,0 +1,294 @@
|
||||
---
|
||||
base_model:
|
||||
- allura-forge/ms32-final-TEXTONLY
|
||||
- ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
|
||||
- anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||
- arcee-ai/Arcee-Blitz
|
||||
- ConicCat/Mistral-Small-3.2-AntiRep-24B
|
||||
- CrucibleLab/M3.2-24B-Loki-V2
|
||||
- DarkArtsForge/Morax-24B-v1
|
||||
- Darkhn/M3.2-24B-Animus-V5.1-Pro
|
||||
- Darkhn/M3.2-24B-Animus-V7.1
|
||||
- Delta-Vector/Rei-24B-KTO
|
||||
- dphn/Dolphin-Mistral-24B-Venice-Edition
|
||||
- Doctor-Shotgun/MS3.2-24B-Magnum-Diamond
|
||||
- FlareRebellion/WeirdCompound-v1.7-24b
|
||||
- Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||
- OddTheGreat/Circuitry_24B_V.3
|
||||
- PocketDoc/Dans-DangerousWinds-V1.1.1-24b
|
||||
- ReadyArt/4.2.0-Broken-Tutu-24b
|
||||
- ReadyArt/Broken-Tutu-24B-Transgression-v2.0
|
||||
- ReadyArt/Dark-Nexus-24B-v2.0
|
||||
- ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.1
|
||||
- spacewars123/Space-Wars-24B-v1.00a
|
||||
- TheDrummer/Cydonia-24B-v2
|
||||
- TheDrummer/Cydonia-24B-v4.2.0
|
||||
- TheDrummer/Cydonia-24B-v4.3
|
||||
- TheDrummer/Magidonia-24B-v4.2.0
|
||||
- TheDrummer/Magidonia-24B-v4.3
|
||||
- TheDrummer/Precog-24B-v1
|
||||
- trashpanda-org/MS-24B-Instruct-Mullein-v0
|
||||
- trashpanda-org/MS3.2-24B-Mullein-v2
|
||||
- TroyDoesAI/BlackSheep-24B
|
||||
- Undi95/MistralThinker-v1.1
|
||||
- zerofata/MS3.2-PaintedFantasy-v2-24B
|
||||
- zerofata/MS3.2-PaintedFantasy-v3-24B
|
||||
datasets:
|
||||
- OccultAI/illuminati_imatrix_v1
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- creative
|
||||
- creative writing
|
||||
- fiction writing
|
||||
- plot generation
|
||||
- sub-plot generation
|
||||
- fiction writing
|
||||
- story generation
|
||||
- scene continue
|
||||
- storytelling
|
||||
- fiction story
|
||||
- science fiction
|
||||
- romance
|
||||
- all genres
|
||||
- story
|
||||
- writing
|
||||
- vivid prosing
|
||||
- vivid writing
|
||||
- fiction
|
||||
- roleplaying
|
||||
- float32
|
||||
- swearing
|
||||
- rp
|
||||
- horror
|
||||
- della
|
||||
- mistral
|
||||
- merge
|
||||
- mergekit
|
||||
widget:
|
||||
- text: "Goetia-24B-v1.3"
|
||||
output:
|
||||
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/DHbuh4efzjCGpxDUciZ_-.jpeg
|
||||
---
|
||||
|
||||
# 📜 Goetia 24B v1.3
|
||||
|
||||
|
||||
|
||||
The "Della Edition" meant to test bridging 2501 and 2503 models. See [this post](https://huggingface.co/Naphula/Goetia-24B-v1.3/discussions/1) and [this other post](https://huggingface.co/Naphula/Q0_Bench/discussions/1?not-for-all-audiences=true#6987717c762f0a45f672e250) for more info.
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
## Merge Details
|
||||
### Merge Methods
|
||||
|
||||
This model was merged using the following merge method:
|
||||
- [DELLA](https://arxiv.org/abs/2406.11617)
|
||||
|
||||
```yaml
|
||||
architecture: MistralForCausalLM
|
||||
models:
|
||||
- model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.05
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.05
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--LatitudeGames--Hearthfire-24B
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.1
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ConicCat--Mistral-Small-3.2-AntiRep-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Undi95--MistralThinker-v1.1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V2
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\Morax-24B-v1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--FlareRebellion--WeirdCompound-v1.7-24b
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--aixonlab--Eurydice-24b-v3.5
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.08
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--allura-forge--ms32-final-TEXTONLY
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Delta-Vector--Rei-24B-KTO
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Doctor-Shotgun--MS3.2-24B-Magnum-Diamond
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--MS3.2-The-Omega-Directive-24B-Unslop-v2.1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--Gryphe--Codex-24B-Small-3.2
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.1
|
||||
# epsilon: 0.1
|
||||
# - model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V1.3
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.15
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--arcee-ai--Arcee-Blitz
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ArliAI--Mistral-Small-24B-ArliAI-RPMax-v1.4
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--PocketDoc--Dans-PersonalityEngine-V1.3.0-24b
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.1
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--Dark-Nexus-24B-v2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V5.1-Pro
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--dphn--Dolphin-Mistral-24B-Venice-Edition
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.01
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TroyDoesAI--BlackSheep-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.01
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v2
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--PocketDoc--Dans-DangerousWinds-V1.1.1-24b
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--trashpanda-org--MS-24B-Instruct-Mullein-v0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--OddTheGreat--Circuitry_24B_V.3
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--spacewars123--Space-Wars-24B-v1.00a
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
# Total Donors: 33
|
||||
# Total Weights: 3.3
|
||||
# Seed: 420
|
||||
merge_method: della
|
||||
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||
parameters:
|
||||
lambda: 1.0
|
||||
normalize: true # key variable to test
|
||||
int8_mask: false
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
# chat_template: auto
|
||||
name: 📜 Goetia-24B-v1.3
|
||||
```
|
||||
51
chat_template.jinja
Normal file
51
chat_template.jinja
Normal file
@@ -0,0 +1,51 @@
|
||||
{%- set today = strftime_now("%Y-%m-%d") %}
|
||||
{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
|
||||
|
||||
{{- bos_token }}
|
||||
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- if messages[0]['content'] is string %}
|
||||
{%- set system_message = messages[0]['content'] %}
|
||||
{%- else %}
|
||||
{%- set system_message = messages[0]['content'][0]['text'] %}
|
||||
{%- endif %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = default_system_message %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message['role'] == 'user' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||
{%- else %}
|
||||
{{- '[INST]' }}
|
||||
{%- for block in message['content'] %}
|
||||
{%- if block['type'] == 'text' %}
|
||||
{{- block['text'] }}
|
||||
{%- elif block['type'] in ['image', 'image_url'] %}
|
||||
{{- '[IMG]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Only text and image blocks are supported in message content!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- '[/INST]' }}
|
||||
{%- endif %}
|
||||
{%- elif message['role'] == 'system' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- else %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- endif %}
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- message['content'] + eos_token }}
|
||||
{%- else %}
|
||||
{{- message['content'][0]['text'] + eos_token }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- raise_exception('Only user, system and assistant roles are supported!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
203
mergekit_config.yml
Normal file
203
mergekit_config.yml
Normal file
@@ -0,0 +1,203 @@
|
||||
architecture: MistralForCausalLM
|
||||
models:
|
||||
- model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.05
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.05
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--LatitudeGames--Hearthfire-24B
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.1
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ConicCat--Mistral-Small-3.2-AntiRep-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Undi95--MistralThinker-v1.1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V2
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\Morax-24B-v1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--FlareRebellion--WeirdCompound-v1.7-24b
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--aixonlab--Eurydice-24b-v3.5
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.08
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--allura-forge--ms32-final-TEXTONLY
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Delta-Vector--Rei-24B-KTO
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Doctor-Shotgun--MS3.2-24B-Magnum-Diamond
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--MS3.2-The-Omega-Directive-24B-Unslop-v2.1
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--Gryphe--Codex-24B-Small-3.2
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.1
|
||||
# epsilon: 0.1
|
||||
# - model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V1.3
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.15
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--arcee-ai--Arcee-Blitz
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--ArliAI--Mistral-Small-24B-ArliAI-RPMax-v1.4
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
# - model: B:\24B\!models--PocketDoc--Dans-PersonalityEngine-V1.3.0-24b
|
||||
# parameters:
|
||||
# density: 0.8
|
||||
# weight: 0.1
|
||||
# epsilon: 0.1
|
||||
- model: B:\24B\!models--ReadyArt--Dark-Nexus-24B-v2.0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.2
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V5.1-Pro
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.15
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--dphn--Dolphin-Mistral-24B-Venice-Edition
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.01
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TroyDoesAI--BlackSheep-24B
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.01
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v2
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--PocketDoc--Dans-DangerousWinds-V1.1.1-24b
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--trashpanda-org--MS-24B-Instruct-Mullein-v0
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--OddTheGreat--Circuitry_24B_V.3
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.1
|
||||
epsilon: 0.1
|
||||
- model: B:\24B\!models--spacewars123--Space-Wars-24B-v1.00a
|
||||
parameters:
|
||||
density: 0.8
|
||||
weight: 0.02
|
||||
epsilon: 0.1
|
||||
# Total Donors: 33
|
||||
# Total Weights: 3.3
|
||||
# Seed: 420
|
||||
merge_method: della
|
||||
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||
parameters:
|
||||
lambda: 1.0
|
||||
normalize: true # key variable to test
|
||||
int8_mask: false
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
# chat_template: auto
|
||||
name: 📜 Goetia-24B-v1.3
|
||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:07954e346e730473c8452af69097f1da87e2a8dec4923823fdd7ea3f7e50fd47
|
||||
size 4907389312
|
||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4224b3df33edbd4e2bab199e96601357b4c288b1c747453d82ea5ebfee2aad03
|
||||
size 4781592832
|
||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:005c3074a2b56a5471b825c819648d5ad0e7c323a87add673ad92adec1fc7c0a
|
||||
size 4781592816
|
||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:df4038523d9fffaf2a60cd9ef985de82c2f740946445959040c3dd31c9f6c687
|
||||
size 4886471592
|
||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:43fec3bc501ff34c8052ea08e9de2f5c731249d02ba2a97809350a5d13e15f70
|
||||
size 4781592832
|
||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:20a222276142588f036d36e363ff191fc861e1dd2f52c72394ffd2613dcc886e
|
||||
size 4781592816
|
||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0df8c0753efc798dffa6376b97dbd92e0b8d85cfb3748ea7326afb2345748c50
|
||||
size 4886471592
|
||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09b708eaf2cc8409c23b75bc7e79ca72806afdc07f93a0b89115d1f8434c9c5e
|
||||
size 4781592832
|
||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b530cc7f61048b6d170e1d9db906fa264bbe36bedd611977cc3ed350e254c018
|
||||
size 4781592800
|
||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e44d34a169e6f75884d74106ec1ef88123f352007a8808b0aea8d16e4c339573
|
||||
size 3774959456
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 47144806400,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00010.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.norm.weight": "model-00010-of-00010.safetensors"
|
||||
}
|
||||
}
|
||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
||||
size 17078037
|
||||
9019
tokenizer_config.json
Normal file
9019
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user