EldritchLabs/Kraken-Della-12B-v1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: EldritchLabs/Kraken-Della-12B-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 06:12:19 +08:00
commit adbf47a7b5
14 changed files with 8999 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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

101
README.md Normal file
View File

@@ -0,0 +1,101 @@
---
base_model:
- aixonlab/Aether-12b
- aixonlab/Zinakha-12b
- allura-org/Bigger-Body-12b
- allura-org/MN-12b-RP-Ink
- allura-org/remnant-mn-12b
- anthracite-org/magnum-v4-12b
- ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
- Babsie/Opulus-12B-v3
- BeaverAI/mistral-doryV2-12b
- crestf411/nemo-sunfall-v0.6.1
- EpistemeAI2/Fireball-Mistral-Nemo-12B-Philos
- EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
- Fizzarolli/MN-12b-Rosier-v1
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- IIEleven11/Kalypso
- intervitens/mini-magnum-12b-v1.1
- jtatman/mistral_nemo_12b_reasoning_psychology_lora
- KOOWEEYUS/BlackSheep-RP-12B
- Lambent/Arsenic-Shahrazad-12B-v2
- Lambent/Arsenic-Shahrazad-12B-v3
- Lambent/arsenic-nemo-unleashed-12B
- Lambent/Gilded-Arsenic-12B
- mistralai/Mistral-Nemo-Instruct-2407
- nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
- nbeerbower/Lyra4-Gutenberg-12B
- nbeerbower/mistral-nemo-bophades-12B
- nbeerbower/mistral-nemo-gutenberg-12B-v3
- nbeerbower/mistral-nemo-gutenberg-12B-v4
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
- nbeerbower/Mistral-Nemo-Gutenberg-Encore-12B
- nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B
- nbeerbower/mistral-nemo-wissenschaft-12B
- NeverSleepHistorical/lumi-nemo-e2.0
- NeverSleep/Lumimaid-v0.2-12B
- nothingiisreal/Celeste-12B-V1.6
- nothingiisreal/MN-12B-Celeste-V1.9
- PocketDoc/Dans-DangerousWinds-V1.1.0-12b
- ReadyArt/Dark-Nexus-12B-v2.0
- ReadyArt/Forgotten-Safeword-12B-v4.0
- ReadyArt/Omega-Darker_The-Final-Directive-12B
- romaingrx/red-teamer-mistral-nemo
- Sao10K/MN-12B-Lyra-v1
- Sao10K/MN-12B-Lyra-v4
- shisa-ai/shisa-v2-mistral-nemo-12b
- sleepdeprived3/Christian-Bible-Expert-v2.0-12B
- SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
- SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2
- TheDrummer/Rivermind-12B-v1
- TheDrummer/Rocinante-12B-v1
- TheDrummer/Rocinante-X-12B-v1
- Trappu/Nemo-Picaro-12B
- Undi95/LocalC-12B-e2.0
- VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
language:
- en
library_name: transformers
license: apache-2.0
tags:
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- fiction writing
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prosing
- vivid writing
- fiction
- roleplaying
- float32
- swearing
- rp
- horror
- della
- mistral
- nemo
- merge
- mergekit
widget:
- text: "Kraken-Della-12B-v1"
output:
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/pUx0TDH4fpFLRsVWYiMB-.png
---
> [!NOTE]
> <span style="color:red; font-weight:bold">⚠️ Note:</span> This model requires **Mistral Tekken** chat template.
>
# Kraken Della 12B v1
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/pUx0TDH4fpFLRsVWYiMB-.png" width=400>

87
chat_template.jinja Normal file
View File

@@ -0,0 +1,87 @@
{%- if messages[0]["role"] == "system" %}
{%- set system_message = messages[0]["content"] %}
{%- set loop_messages = messages[1:] %}
{%- else %}
{%- set loop_messages = messages %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
{%- set ns = namespace() %}
{%- set ns.index = 0 %}
{%- for message in loop_messages %}
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
{%- endif %}
{%- set ns.index = ns.index + 1 %}
{%- endif %}
{%- endfor %}
{{- bos_token }}
{%- for message in loop_messages %}
{%- if message["role"] == "user" %}
{%- if tools is not none and (message == user_messages[-1]) %}
{{- "[AVAILABLE_TOOLS][" }}
{%- for tool in tools %}
{%- set tool = tool.function %}
{{- '{"type": "function", "function": {' }}
{%- for key, val in tool.items() if key != "return" %}
{%- if val is string %}
{{- '"' + key + '": "' + val + '"' }}
{%- else %}
{{- '"' + key + '": ' + val|tojson }}
{%- endif %}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- "}}" }}
{%- if not loop.last %}
{{- ", " }}
{%- else %}
{{- "]" }}
{%- endif %}
{%- endfor %}
{{- "[/AVAILABLE_TOOLS]" }}
{%- endif %}
{%- if loop.last and system_message is defined %}
{{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
{%- else %}
{{- "[INST]" + message["content"] + "[/INST]" }}
{%- endif %}
{%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
{{- "[TOOL_CALLS][" }}
{%- for tool_call in message.tool_calls %}
{%- set out = tool_call.function|tojson %}
{{- out[:-1] }}
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
{%- endif %}
{{- ', "id": "' + tool_call.id + '"}' }}
{%- if not loop.last %}
{{- ", " }}
{%- else %}
{{- "]" + eos_token }}
{%- endif %}
{%- endfor %}
{%- elif message["role"] == "assistant" %}
{{- message["content"] + 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": ' + content|string + ", " }}
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
{%- endif %}
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
{%- else %}
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
{%- endif %}
{%- endfor %}

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.6",
"use_cache": true,
"vocab_size": 131077
}

278
mergekit_config.yml Normal file
View File

@@ -0,0 +1,278 @@
base_model: B:/12B/models--mistralai--Mistral-Nemo-Instruct-2407
models:
- model: B:/12B/models--aixonlab--Aether-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--aixonlab--Zinakha-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--allura-org--Bigger-Body-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--allura-org--MN-12b-RP-Ink
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--allura-org--remnant-mn-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--anthracite-org--magnum-v4-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--ArliAI--Mistral-Nemo-12B-ArliAI-RPMax-v1.2
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Babsie--Opulus-12B-v3
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--BeaverAI--mistral-doryV2-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--crestf411--nemo-sunfall-v0.6.1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--EpistemeAI2--Fireball-Mistral-Nemo-12B-Philos
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--EpistemeAI--Mistral-Nemo-Instruct-12B-Philosophy-Math
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Fizzarolli--MN-12b-Rosier-v1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--HumanLLMs--Human-Like-Mistral-Nemo-Instruct-2407
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--IIEleven11--Kalypso
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--intervitens--mini-magnum-12b-v1.1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--jtatman--mistral_nemo_12b_reasoning_psychology_lora
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--KOOWEEYUS--BlackSheep-RP-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Lambent--Arsenic-Shahrazad-12B-v2
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Lambent--Arsenic-Shahrazad-12B-v3
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Lambent--arsenic-nemo-unleashed-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Lambent--Gilded-Arsenic-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--mistralai--Mistral-Nemo-Instruct-2407
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--Lyra-Gutenberg-mistral-nemo-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--Lyra4-Gutenberg-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--mistral-nemo-bophades-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--mistral-nemo-gutenberg-12B-v3
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--mistral-nemo-gutenberg-12B-v4
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Doppel-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Encore-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Vitus-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nbeerbower--mistral-nemo-wissenschaft-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--NeverSleepHistorical--lumi-nemo-e2.0
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--NeverSleep--Lumimaid-v0.2-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nothingiisreal--Celeste-12B-V1.6
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--nothingiisreal--MN-12B-Celeste-V1.9
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--PocketDoc--Dans-DangerousWinds-V1.1.0-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--ReadyArt--Dark-Nexus-12B-v2.0
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--ReadyArt--Forgotten-Safeword-12B-v4.0
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--ReadyArt--Omega-Darker_The-Final-Directive-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--romaingrx--red-teamer-mistral-nemo
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Sao10K--MN-12B-Lyra-v1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Sao10K--MN-12B-Lyra-v4
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--shisa-ai--shisa-v2-mistral-nemo-12b
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--sleepdeprived3--Christian-Bible-Expert-v2.0-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--SuperbEmphasis--Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--TheDrummer--Rivermind-12B-v1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--TheDrummer--Rocinante-12B-v1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--TheDrummer--Rocinante-X-12B-v1
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Trappu--Nemo-Picaro-12B
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--Undi95--LocalC-12B-e2.0
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
- model: B:/12B/models--VAGOsolutions--SauerkrautLM-Nemo-12b-Instruct
parameters:
density: 0.9
weight: 0.03
epsilon: 0.099
merge_method: della
parameters:
lambda: 1.0
normalize: false
int8_mask: false
dtype: float32
out_dtype: bfloat16
tokenizer:
source: union
chat_template: auto
name: 🦑‍ Kraken-12B-v1

3
model-00001-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:613feaf64cee39ad8f4ac47a83bbe7fa80567290bcc0757155b08f9f1c94d08f
size 4865591736

3
model-00002-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27085b205846ae38ad0d1ef38e351a803b1b31b63dc2260fd536cadda8e20330
size 4907529456

3
model-00003-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:58cfd61eec89b54f5ddc8714c1787a204381bac7f914b473fc1601deb3fd5f63
size 4907529464

3
model-00004-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd049e2f5f80b650ec901a357ca5f8c7d949b2f1fb8544361417073a6aac9daf
size 4907529456

3
model-00005-of-00005.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9652fa0f742cb80a84d4dbf911e71bf703ae96aa188425a273b2f935ae76f462
size 4907529392

371
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,371 @@
{
"metadata": {
"total_size": 24495667200,
"mergekit_version": "0.1.4"
},
"weight_map": {
"lm_head.weight": "model-00001-of-00005.safetensors",
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
"model.norm.weight": "model-00005-of-00005.safetensors"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dc401e45928c561d0a44f2a6331dcca047c233c5ef37903ebb49f3ebb62bc554
size 17079235

8059
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff