初始化项目，由ModelHub XC社区提供模型
Model: ShyliaSafetensors/EnceladusHyperStock-24B Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
|||||||
|
*.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
|
||||||
|
impactframe.gif filter=lfs diff=lfs merge=lfs -text
|
||||||
|
enceladus.gif filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
16
1merge_configDARE-TIES.yml
Normal file
16
1merge_configDARE-TIES.yml
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
merge_method: dare_ties
|
||||||
|
base_model: R:\WeirdCompound
|
||||||
|
models:
|
||||||
|
- model: R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
parameters:
|
||||||
|
weight: 0.50
|
||||||
|
density: 0.55
|
||||||
|
- model: R:\Cydonia-24B-Heretic-v4
|
||||||
|
parameters:
|
||||||
|
weight: 0.45
|
||||||
|
density: 0.50
|
||||||
|
- model: R:\WeirdCompound
|
||||||
|
parameters:
|
||||||
|
weight: 0.45
|
||||||
|
density: 0.40
|
||||||
|
dtype: bfloat16
|
||||||
8
2merge_configMODEL-STOCK.yml
Normal file
8
2merge_configMODEL-STOCK.yml
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
merge_method: model_stock
|
||||||
|
base_model: R:\MergeOutput\EnceladusDare-ties
|
||||||
|
models:
|
||||||
|
- model: R:\Cydonia-24B-Heretic-v4
|
||||||
|
- model: R:\MS3.2-PaintedFantasy-v2-24B
|
||||||
|
- model: R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
- model: R:\WeirdCompound
|
||||||
|
dtype: bfloat16
|
||||||
10
3merge_configMODEL-STOCK.yml
Normal file
10
3merge_configMODEL-STOCK.yml
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
merge_method: model_stock
|
||||||
|
base_model: R:\MergeOutput\EnceladusModelStock-Heretic
|
||||||
|
models:
|
||||||
|
- model: R:\MergeOutput\EnceladusModelStock-Heretic
|
||||||
|
- model: R:\Sakura-24B-Spice
|
||||||
|
- model: R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
- model: R:\WeirdCompound
|
||||||
|
- model: R:\Broken-Tutu-24B-Unslop-v2.0
|
||||||
|
- model: R:\Cydonia-24B-Heretic-v4
|
||||||
|
dtype: bfloat16
|
||||||
150
README.md
Normal file
150
README.md
Normal file
@@ -0,0 +1,150 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- coder3101/Cydonia-24B-v4.3-heretic-v4
|
||||||
|
- FlareRebellion/WeirdCompound-v1.7-24b
|
||||||
|
- WasamiKirua/Sakura-24B-Spice
|
||||||
|
- ReadyArt/Broken-Tutu-24B-Unslop-v2.0
|
||||||
|
- zerofata/MS3.2-PaintedFantasy-v4.1-24B
|
||||||
|
- DavidAU/Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- mergekit
|
||||||
|
- merge
|
||||||
|
- model-stock
|
||||||
|
- mistral
|
||||||
|
- 24b
|
||||||
|
- dare-ties
|
||||||
|
- uncensored
|
||||||
|
- roleplay
|
||||||
|
- thinking
|
||||||
|
- conversational
|
||||||
|
- not-for-all-audiences
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
# EnceladusHyperStock
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
**EnceladusHyperStock-24B** is ***Experimental*** version of my previous multimerge model; 'VeryWeirdDolphinMix-V1-24B-Heretic'. And this doesnt mean this merge-model is better.
|
||||||
|
|
||||||
|
The goal was to create a model that handles complex scenes, story-writing and role-play with creativitiy and consistent.
|
||||||
|
|
||||||
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||||
|
|
||||||
|
---
|
||||||
|
## Thinking Capability
|
||||||
|
|
||||||
|
This model can think if these tags used:
|
||||||
|
|
||||||
|
```
|
||||||
|
<thinking>
|
||||||
|
|
||||||
|
</thinking>
|
||||||
|
```
|
||||||
|
---
|
||||||
|
|
||||||
|
## Recommended Settings
|
||||||
|
|
||||||
|
These are my recommended settings.
|
||||||
|
|
||||||
|
| Setting | Value |
|
||||||
|
|---|---|
|
||||||
|
| Temperature | 0.65 - 0.85 |
|
||||||
|
| Min P | 0.05 - 0.1 |
|
||||||
|
| Repetition penalty | 1.05 - 1.1 |
|
||||||
|
| Top P | 0.75 - 0.95 |
|
||||||
|
| Adaptive-p target | 0.70 - 0.9 |
|
||||||
|
| Adaptive-p decay | 0.9 |
|
||||||
|
|
||||||
|
Use the **Mistral V7 Tekken** Template.
|
||||||
|
|
||||||
|
|
||||||
|
I recommend some tinkering with these samplers. I personally use Adaptive-P instead of 'DRY repetition penalty' or 'Rep pen'.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Intended Use
|
||||||
|
|
||||||
|
- Long-form uncensored roleplay and collaborative storytelling
|
||||||
|
- Uncensored creative writing
|
||||||
|
- Complex instruction following with visible reasoning via `<thinking>`
|
||||||
|
- Conversational AI with personality depth
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Disclaimer
|
||||||
|
|
||||||
|
This model is **uncensored** and intended for adult, research, fictional story, and creative use. It may produce content that some users find offensive or inappropriate. Use responsibly.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Merge Details
|
||||||
|
### Merge Methods
|
||||||
|
|
||||||
|
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) and [Dare-Ties](https://arxiv.org/abs/2306.01708) merge methods.
|
||||||
|
|
||||||
|
### Models Merged
|
||||||
|
|
||||||
|
The following models were included in the merge:
|
||||||
|
* R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
* R:\Sakura-24B-Spice
|
||||||
|
* R:\Cydonia-24B-Heretic-v4
|
||||||
|
* R:\WeirdCompound
|
||||||
|
* R:\Broken-Tutu-24B-Unslop-v2.0
|
||||||
|
* R:\MergeOutput\EnceladusDare-ties(second step model)
|
||||||
|
|
||||||
|
### Configuration
|
||||||
|
|
||||||
|
The following YAML configuration(s) was used to produce this model:
|
||||||
|
---
|
||||||
|
- first step
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
merge_method: dare_ties
|
||||||
|
base_model: R:\WeirdCompound
|
||||||
|
models:
|
||||||
|
- model: R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
parameters:
|
||||||
|
weight: 0.50
|
||||||
|
density: 0.55
|
||||||
|
- model: R:\Cydonia-24B-Heretic-v4
|
||||||
|
parameters:
|
||||||
|
weight: 0.45
|
||||||
|
density: 0.50
|
||||||
|
- model: R:\WeirdCompound
|
||||||
|
parameters:
|
||||||
|
weight: 0.45
|
||||||
|
density: 0.40
|
||||||
|
dtype: bfloat16
|
||||||
|
```
|
||||||
|
---
|
||||||
|
- second step (I've used Heretic in this step, 86/100 refusals to: 8/100 refusals with 0.0063 KL Divergence. Trial 92.)
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
merge_method: model_stock
|
||||||
|
base_model: R:\MergeOutput\EnceladusDare-ties
|
||||||
|
models:
|
||||||
|
- model: R:\Cydonia-24B-Heretic-v4
|
||||||
|
- model: R:\MS3.2-PaintedFantasy-v2-24B
|
||||||
|
- model: R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
- model: R:\WeirdCompound
|
||||||
|
dtype: bfloat16
|
||||||
|
```
|
||||||
|
---
|
||||||
|
- last step
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
merge_method: model_stock
|
||||||
|
base_model: R:\MergeOutput\EnceladusModelStock-Heretic
|
||||||
|
models:
|
||||||
|
- model: R:\MergeOutput\EnceladusModelStock-Heretic
|
||||||
|
- model: R:\Sakura-24B-Spice
|
||||||
|
- model: R:\Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
|
||||||
|
- model: R:\WeirdCompound
|
||||||
|
- model: R:\Broken-Tutu-24B-Unslop-v2.0
|
||||||
|
- model: R:\Cydonia-24B-Heretic-v4
|
||||||
|
dtype: bfloat16
|
||||||
|
```
|
||||||
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 %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"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_parameters": {
|
||||||
|
"rope_theta": 1000000000.0,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.57.6",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 131072
|
||||||
|
}
|
||||||
3
enceladus.gif
Normal file
3
enceladus.gif
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a1cb972236a1b686c92e04f07985e4a3e4842c120c4a75240f24e446a418b7e5
|
||||||
|
size 235443
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"transformers_version": "5.5.0",
|
||||||
|
"use_cache": true
|
||||||
|
}
|
||||||
3
hereticresults1.txt
Normal file
3
hereticresults1.txt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
[Trial 92] Refusals: 8/100, KL divergence: 0.0063
|
||||||
|
|
||||||
|
Initial refusals: 85/100
|
||||||
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 sha256:517da7f403bfd5c10600c5ea74678c2063555ae2e4427f7342a4da9ff89356c4
|
||||||
|
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 sha256:231895854a176bdf820c9e5fb2fd365135005fcc71b4b21c7d55a15afc364404
|
||||||
|
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:f8bfc3d22d0fd8238c7b879385c0ffd99ca8169cd525e873b9bba11aad561a78
|
||||||
|
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 sha256:407c5cfa06defb41b553dcc7b619e4533be1f5d71230b55cab2b32100f1ce6b8
|
||||||
|
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 sha256:74f0627b1ada1124af92fe2d1a2917ea5e3a11611da2094a186d15b1093a808c
|
||||||
|
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 sha256:3480bed05649a62c3b8e44301a3c3f33562ed992f8089ae70e70356699b08277
|
||||||
|
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 sha256:2980ff0d9ea8d619b1c02cfd906f8801bc545cce9f4ad9e62431fb6db2e383e7
|
||||||
|
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 sha256:5ec95006d57b400218ef83da33af10affbe690a0e98c65d03b27978781217455
|
||||||
|
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 sha256:3bad4ed25e3e7f89d6847566101f9ea72ea1b04db919e5f95ff95278221ce32d
|
||||||
|
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 sha256:056f8e03c0c28afb85268ab1e1b818cf6baa06e8ef23ce806bfc8953fd64fd13
|
||||||
|
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
|
||||||
9020
tokenizer_config.json
Normal file
9020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user