初始化项目，由ModelHub XC社区提供模型
Model: DarkArtsForge/Magistaroth-24B-v1.1 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
47
README.md
Normal file
47
README.md
Normal file
@@ -0,0 +1,47 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model:
|
||||
- DarkArtsForge/Magistaroth-24B-v1
|
||||
- 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:
|
||||
- pdq
|
||||
- merge
|
||||
- mergekit
|
||||
widget:
|
||||
- text: "Magistaroth 24B v1.1"
|
||||
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 v1.1
|
||||
|
||||
|
||||
|
||||
# Merge Method
|
||||
A custom merge method known as `pdq` has been invented. Instead of using its own yaml, it acts as a post-merge processor which applies directly to the merged model using the [original yaml](https://huggingface.co/DarkArtsForge/Magistaroth-24B-v1/raw/main/mergekit_config.yml). `pdq` aims to enhance creativity by re-scanning the original donor models, encouraging them to explore the 'dark matter' regions of the vectors to synergistically augment the merged base with more unique novelty. For **Magistaroth v1.1**, I tested both the v1 `Della → PDQ → MPOA` and `Della → MPOA → PDQ`.
|
||||
|
||||
It turns out that both are very creative, and the `MPOA → PDQ` is interesting because it doesn't re-introduce any refusals, however, `PDQ → MPOA` is much smarter. The difference in Q0 bench reflects this (9451 vs 12648). `Scale 1.2` was the ablation threshold required to disable refusals. This has resulted in the most creative, detailed, and uncensored variant of the configurations tested.
|
||||
|
||||
### Bugs
|
||||
A small risk of increased artifacts (missing spaces, word misspelled or repeated) might be noticed due to `pdq` pushing the limits of what's possible with transformers. These are rare and can be edited out if needed.
|
||||
|
||||
### Fully Uncensored
|
||||
An unablated PDQ version was also tested (it has refusals) but it seems the ablated versions are more popular so I'm just releasing this one for now.
|
||||
|
||||
### Settings
|
||||
- Recommended `temp 1.0` and `topnsigma 1.25`
|
||||
- `Mistral Tekken` chat template
|
||||
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
|
||||
}
|
||||
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 sha256:217ea4df8748f6ac14bd4d7d380ae91151809fd958a5dc63c128775c2fb21a54
|
||||
size 4907389280
|
||||
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 sha256:2473db8bdd116a5751f1e48c4f2fe65dfa76a969177c594396888003c1c70917
|
||||
size 4781592800
|
||||
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 sha256:4dd955797a7b0a5113c91046e5b92e778c5f520674b25b26e90c3f0f2503c66a
|
||||
size 4781592784
|
||||
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 sha256:6b4661770c69dc62e1f8e329211e2f72b833c1f8e50f5cf8c0717f13b9ed1c22
|
||||
size 4886471560
|
||||
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:fd405a74202784f8d3a7c320b27d002f42de0d6571c6915cecc43ce731eb5cb9
|
||||
size 4781592800
|
||||
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 sha256:6ac547e23f1ab72127d0eb48b3c8c9b4bfb85d54df50a41c9a4b92e7c0f91ff9
|
||||
size 4781592784
|
||||
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 sha256:759ea2c6d283c56fd73cbe70f941eee87906d28dfe207f8c4e5d2908c3ba4bf5
|
||||
size 4886471568
|
||||
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 sha256:72c48741464371e3bf665b7e067220020f97696f1d2581d0be64af5dd85796f9
|
||||
size 4781592800
|
||||
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 sha256:06a3b87d693064834d15b255a55ec8c0087f8df49bf0b41fec43cbb9eb81d70e
|
||||
size 4781592768
|
||||
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 sha256:598236a48f7e83a7ad6f0d367fc9ce9719c7f8e905ebba83f80ad2d0c31bee30
|
||||
size 3774959424
|
||||
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