初始化项目，由ModelHub XC社区提供模型
Model: DarkArtsForge/Magistaroth-24B-v1 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
|
||||
Magistaroth.png filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
ablit_proj filter=lfs diff=lfs merge=lfs -text
|
||||
3
Magistaroth.png
Normal file
3
Magistaroth.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:308f0b38f4fc1841f8bfe264e2912732b767a424b5e21a793e7054719ae3f0ce
|
||||
size 1617803
|
||||
83
README.md
Normal file
83
README.md
Normal file
@@ -0,0 +1,83 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model:
|
||||
- mistralai/Magistral-Small-2509
|
||||
- Gryphe/Tiamat-24B-Magistral
|
||||
- TheDrummer/Magidonia-24B-v4.3
|
||||
- TheDrummer/Precog-24B-v1
|
||||
- zerofata/MS3.2-PaintedFantasy-v3-24B
|
||||
- zerofata/MS3.2-PaintedFantasy-v4.1-24B
|
||||
datasets:
|
||||
- OccultAI/illuminati_imatrix_v1
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- DELLA
|
||||
- merge
|
||||
- mergekit
|
||||
widget:
|
||||
- text: "Magistaroth 24B v1"
|
||||
output:
|
||||
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/n2QI4o6Xx2d5QUhsLvmt3.png
|
||||
---
|
||||
|
||||
> [!CAUTION]
|
||||
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **Mistral Tekken** chat template.
|
||||
>
|
||||
|
||||
# 🌌 Magistaroth 24B v1
|
||||
|
||||
|
||||
|
||||
A highly creative merge. Some refusals but you can use jailbreaks or ablate the model. A normtrue version was tested. Normfalse did better overall, it was slightly less censored, more detailed and creative.
|
||||
|
||||
Scores 14152 at Q0 Bench (Pass Q0G).
|
||||
|
||||
This model was merged using the following merge method: <a href="https://arxiv.org/abs/2406.11617">DELLA</a>
|
||||
|
||||
```yaml
|
||||
architecture: MistralForCausalLM
|
||||
models:
|
||||
- model: B:\24B\!models--mistralai--Magistral-Small-2509\textonly
|
||||
- model: B:\24B\!models--Gryphe--Tiamat-24B-Magistral\textonly
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v4.1-24B
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
# Seed: 420
|
||||
merge_method: della
|
||||
base_model: B:\24B\!models--mistralai--Magistral-Small-2509\textonly
|
||||
parameters:
|
||||
lambda: 1.0
|
||||
normalize: false
|
||||
int8_mask: false
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
# chat_template: auto
|
||||
name: 🌌 Magistaroth-24B-v1
|
||||
```
|
||||
|
||||
|
||||
3
ablit_proj
Normal file
3
ablit_proj
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77645bdb204fac92521f1e2788dd748a78f1a33a3a8ea140518a05bb84833867
|
||||
size 2492022
|
||||
112
chat_template.jinja
Normal file
112
chat_template.jinja
Normal file
@@ -0,0 +1,112 @@
|
||||
{%- set default_system_message = 'First draft your thinking process (inner monologue) until you arrive at a response. Format your response using Markdown, and use LaTeX for any mathematical equations. Write both your thoughts and the response in the same language as the input.\n\nYour thinking process must follow the template below:[THINK]Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate the response. Use the same language as the input.[/THINK]Here, provide a self-contained response.' %}
|
||||
|
||||
{{- bos_token }}
|
||||
|
||||
{#- Extract system message if present -#}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- if messages[0]['content'] is string %}
|
||||
{%- set raw_system_message = messages[0]['content'] %}
|
||||
{%- else %}
|
||||
{%- set raw_system_message = messages[0]['content'][0]['text'] %}
|
||||
{%- endif %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set raw_system_message = "" %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
|
||||
{#- Detect THINK flag by searching for exact phrase "/think" -#}
|
||||
{%- if "/think" in raw_system_message %}
|
||||
{%- set THINK = True %}
|
||||
{%- else %}
|
||||
{%- set THINK = False %}
|
||||
{%- endif %}
|
||||
|
||||
{#- Apply logic depending on THINK flag -#}
|
||||
{%- if THINK %}
|
||||
{%- if raw_system_message|length > 0 %}
|
||||
{%- set system_message = default_system_message + "\n\n" + raw_system_message %}
|
||||
{%- else %}
|
||||
{%- set system_message = default_system_message %}
|
||||
{%- endif %}
|
||||
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||
{%- else %}
|
||||
{%- if raw_system_message|length > 0 %}
|
||||
{{- '[SYSTEM_PROMPT]' + raw_system_message + '[/SYSTEM_PROMPT]' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
|
||||
|
||||
{#- Tool description appended ONLY to last user message. Edits made by Unsloth #}
|
||||
{%- set tools_description = "" %}
|
||||
{%- set has_tools = false %}
|
||||
|
||||
{%- if tools is defined and tools is not none and tools|length > 0 %}
|
||||
{%- set has_tools = true %}
|
||||
{%- set tools_description = "[AVAILABLE_TOOLS]" + (tools | tojson) + "[/AVAILABLE_TOOLS]" %}
|
||||
{{- tools_description }}
|
||||
{%- endif %}
|
||||
|
||||
{%- 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' %}
|
||||
{%- if block['text'] is defined %}
|
||||
{{- block['text'] }}
|
||||
{%- else %}
|
||||
{{- block['content'] }}
|
||||
{%- endif %}
|
||||
{%- 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'] }}
|
||||
{%- elif message['content'] is iterable %}
|
||||
{{- message['content'][0]['text'] }}
|
||||
{%- endif %}
|
||||
|
||||
{%- if message['tool_calls'] is defined and message['tool_calls'] is not none %}
|
||||
{%- for tool in message['tool_calls'] %}
|
||||
{%- set arguments = tool['function']['arguments'] %}
|
||||
{%- if arguments is not string %}
|
||||
{%- set arguments = arguments|tojson %}
|
||||
{%- endif %}
|
||||
{{- "[TOOL_CALLS]" + tool['function']['name'] + "[ARGS]" + arguments }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
|
||||
{{- eos_token }}
|
||||
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{{- "[TOOL_RESULTS]" + content|string + "[/TOOL_RESULTS]" }}
|
||||
|
||||
{%- else %}
|
||||
{{- raise_exception('Only user, system, assistant and tool roles are supported!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{#- Licensed under the Apache License, Version 2.0 (the "License") #}
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"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,
|
||||
"pad_token_id": 11,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
41
mergekit_config.yml
Normal file
41
mergekit_config.yml
Normal file
@@ -0,0 +1,41 @@
|
||||
architecture: MistralForCausalLM
|
||||
models:
|
||||
- model: B:\24B\!models--mistralai--Magistral-Small-2509\textonly
|
||||
- model: B:\24B\!models--Gryphe--Tiamat-24B-Magistral\textonly
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v4.1-24B
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 0.4
|
||||
epsilon: 0.099
|
||||
# Seed: 420
|
||||
merge_method: della
|
||||
base_model: B:\24B\!models--mistralai--Magistral-Small-2509\textonly
|
||||
parameters:
|
||||
lambda: 1.0
|
||||
normalize: false
|
||||
int8_mask: false
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
# chat_template: auto
|
||||
name: 🌌 Magistaroth-24B-v1
|
||||
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 sha256:0efef48d440bf6aaa09928944c4ef787652175b543ed073df2b2d0bdcfb60d25
|
||||
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:a01353a08630595261326d8170b00a8edf2023c527afab4198b2db5838e04ae4
|
||||
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:bf27597db5bfee33ad8a52b44b5cb48367fc3a0e8fef3dbed284427bef6431b9
|
||||
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 sha256:3b02464c060cb699fb1210285009f25dec5befe4728d42ea7afe126c899a5d6a
|
||||
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:e0f754a142b150b187131189e33e996ce266138075bc6a9f992997f23c88f9fc
|
||||
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 sha256:52e60997e7b267c4ed73411919778f5027c76d494889abeba87439cf5f879d34
|
||||
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:da279f7ead8baa4b4fabf7c2d74b88c4178a3a915c8cafaf3e7ed8ac62c948b6
|
||||
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:e3263ac90cfcc72f7ce2b5ff0d402937a6f7777b504c718acc9ead6fab492650
|
||||
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:d7da10b67f320bf827d537a24be5c95b3e22c171c2fd9c57703228ede05ffc46
|
||||
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 sha256:397a7ff8c0e33abfe4b0ba07b2c23e9e9ead19f6d83db5dc949bbe2011f22c5f
|
||||
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 sha256:158915c7c928301e0d32f1da363e45c294d907bd4c64a8e855f0bd1a47b9e870
|
||||
size 17078001
|
||||
9021
tokenizer_config.json
Normal file
9021
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user