初始化项目，由ModelHub XC社区提供模型
Model: gghfez/Mistral-Small-3.2-24B-Instruct-hf-AWQ 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
|
||||
11
README.md
Normal file
11
README.md
Normal file
@@ -0,0 +1,11 @@
|
||||
---
|
||||
base_model:
|
||||
- gghfez/Mistral-Small-3.2-24B-Instruct-hf
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- awq
|
||||
- mistral
|
||||
---
|
||||
25
chat_template.jinja
Normal file
25
chat_template.jinja
Normal file
@@ -0,0 +1,25 @@
|
||||
{%- 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' %}
|
||||
{%- set system_message = messages[0]['content'] %}
|
||||
{%- 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' %}
|
||||
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||
{%- elif message['role'] == 'system' %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{{- message['content'] + eos_token }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Only user, system and assistant roles are supported!') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"modules_to_not_convert": null,
|
||||
"quant_method": "awq",
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a8defe43302884300cc63e0b806af1994b08aa775948c233d95e21d971b6a021
|
||||
size 4921581912
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2d6042c23fbaee9c96720e55653d277274d30f4cab66279bd389f668c0cb8c91
|
||||
size 4995915728
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5eef2f76ad658833c2070d802b8f63b12e4350d04c9f8a79613365a15816a33b
|
||||
size 4316873088
|
||||
930
model.safetensors.index.json
Normal file
930
model.safetensors.index.json
Normal file
@@ -0,0 +1,930 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14234265600
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
1025
special_tokens_map.json
Normal file
1025
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
||||
size 17078037
|
||||
9018
tokenizer_config.json
Normal file
9018
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user