初始化项目，由ModelHub XC社区提供模型
Model: AlSamCur123/Mistral-Small-24B-Instruct-2501-continued 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
|
||||
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
||||
---
|
||||
base_model: unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- transformers
|
||||
- unsloth
|
||||
- mistral
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# Uploaded finetuned model
|
||||
|
||||
- **Developed by:** AlSamCur123
|
||||
- **License:** apache-2.0
|
||||
- **Finetuned from model :** unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit
|
||||
|
||||
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||||
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 %}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"torch_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": 32768,
|
||||
"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_scaling": null,
|
||||
"rope_theta": 100000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.3.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87366ef5282111606d9c65c1504f033a9c409ca687db1fce83ce0dd7e2705950
|
||||
size 4781571736
|
||||
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 sha256:895e20744075f30fc81ac708450439ffed459f614fd7daaa588da9f673df3a06
|
||||
size 4781592784
|
||||
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 sha256:211d571168f45b5723335ea382474e35f30b007435567b00ca25d363e2b9a25b
|
||||
size 4781592800
|
||||
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:dada7f072bd0f85b67c9bbc87e261c6410c29e4f5ccd25da4332d12449c4be38
|
||||
size 4886471600
|
||||
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:dd3035dd552f2fbf1302c242d98e465f256a019bc37c4e00234ff4d6cf2afdaf
|
||||
size 4781592824
|
||||
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:a4b52c28bb9953f123d846f5fbaa44433c44af4263c1555a73028a80842b22f8
|
||||
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:fcfab53d28a7fa45a15a6b5381552c130136dd73f9f65760c1bad500ef4211ae
|
||||
size 4886471600
|
||||
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:fffdc555d9e1b6c269441cb7ba6558faabdd0f9d1f890fd36e040cdb41e84643
|
||||
size 4781592824
|
||||
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:e214527e4632ad06087a029df7093c7ca9010f80b0e0d95df134087f333c85b0
|
||||
size 4781592816
|
||||
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 sha256:9f2fde16001f05a58c8fdc437fba509b89095492164291fe06b682c13845b399
|
||||
size 3900777072
|
||||
370
model.safetensors.index.json
Normal file
370
model.safetensors.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 47144806400
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00010-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-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-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:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
||||
size 17078037
|
||||
9021
tokenizer_config.json
Normal file
9021
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user