初始化项目，由ModelHub XC社区提供模型
Model: 24B-Suite/Mergedonia-KARCHER-24B-v1 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
|
||||
34
README.md
Normal file
34
README.md
Normal file
@@ -0,0 +1,34 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model:
|
||||
- Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||
- TheDrummer/Cydonia-24B-v4.3
|
||||
- TheDrummer/Magidonia-24B-v4.3
|
||||
- TheDrummer/Precog-24B-v1
|
||||
- TheDrummer/Rivermind-24B-v1
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- mistral
|
||||
---
|
||||
|
||||
```yaml
|
||||
architecture: MistralForCausalLM
|
||||
models:
|
||||
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||
- model: B:\24B\!models--TheDrummer--Rivermind-24B-v1
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||||
merge_method: karcher
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
parameters:
|
||||
tol: 1.0e-9
|
||||
max_iter: 1000
|
||||
tokenizer_source: union
|
||||
name: Mergedonia-Karcher-24B-v1
|
||||
```
|
||||
51
chat_template.jinja
Normal file
51
chat_template.jinja
Normal file
@@ -0,0 +1,51 @@
|
||||
{%- set today = strftime_now("%Y-%m-%d") %}
|
||||
{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
|
||||
|
||||
{{- bos_token }}
|
||||
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- if messages[0]['content'] is string %}
|
||||
{%- set system_message = messages[0]['content'] %}
|
||||
{%- else %}
|
||||
{%- set system_message = messages[0]['content'][0]['text'] %}
|
||||
{%- endif %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = default_system_message %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message['role'] == 'user' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||
{%- else %}
|
||||
{{- '[INST]' }}
|
||||
{%- for block in message['content'] %}
|
||||
{%- if block['type'] == 'text' %}
|
||||
{{- block['text'] }}
|
||||
{%- elif block['type'] in ['image', 'image_url'] %}
|
||||
{{- '[IMG]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Only text and image blocks are supported in message content!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- '[/INST]' }}
|
||||
{%- endif %}
|
||||
{%- elif message['role'] == 'system' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- else %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- endif %}
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{%- if message['content'] is string %}
|
||||
{{- message['content'] + eos_token }}
|
||||
{%- else %}
|
||||
{{- message['content'][0]['text'] + eos_token }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- raise_exception('Only user, system and assistant roles are supported!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
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": 131076
|
||||
}
|
||||
15
mergekit_config.yml
Normal file
15
mergekit_config.yml
Normal file
@@ -0,0 +1,15 @@
|
||||
architecture: MistralForCausalLM
|
||||
models:
|
||||
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||
- model: B:\24B\!models--TheDrummer--Rivermind-24B-v1
|
||||
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||||
merge_method: karcher
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
parameters:
|
||||
tol: 1.0e-9
|
||||
max_iter: 1000
|
||||
tokenizer_source: union
|
||||
name: Mergedonia-Karcher
|
||||
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 sha256:2ccd5e6f0934f9cf23fad2de5782e4542fa34676aebb2666a2ef4a0bf5dbc650
|
||||
size 4907471232
|
||||
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 sha256:0c5659ed1e3f82eb7f55f729c6a4bf86149332188335854027b4c16b533a310a
|
||||
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:bfa5880f7866d4fcf9f002034da3b384494f4cbd2222348e3e4c012a229bbc5b
|
||||
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 sha256:5afe45a833a636d5b68beb6939f4b7591bf3d5e36ac9057788df8620ff1b9cf0
|
||||
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:d704ec8d176c0f4a9bf0d56558967a23a899125b962faf4cbde79987553fe856
|
||||
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 sha256:390a7860418da2c74c7096c3a41cb4f41ec50d050b331763ca1d3fa4c7bc992f
|
||||
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 sha256:73e013fa9e91137274fb19461cdc556f1aee96a3f20f20255cc37d047bc73680
|
||||
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 sha256:1fd7acd2b1382b0e8c43a7f1caed29f7a3c0c17339c0ee1f63eaf939e1acbc57
|
||||
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 sha256:090e8c13aaeee3790dd9a3d2ec1ee45fb93d44916e1736691fdfba2107313ce9
|
||||
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 sha256:4e61addeda39b15e0ddaf321c28594f1da41e1145015a36a0274c70d9aa7a868
|
||||
size 3774959456
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 47144888320,
|
||||
"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 sha256:05230ffd53b91df6d926b85fd13c0899a5535901d87d063fea07e31871bfd6d7
|
||||
size 17078775
|
||||
9051
tokenizer_config.json
Normal file
9051
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user