初始化项目，由ModelHub XC社区提供模型
Model: CanisAI1/CanisAI-Retriever-1-5 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
|
||||
46
README.md
Normal file
46
README.md
Normal file
@@ -0,0 +1,46 @@
|
||||
---
|
||||
tags:
|
||||
- autotrain
|
||||
- text-generation-inference
|
||||
- text-generation
|
||||
- peft
|
||||
library_name: transformers
|
||||
base_model: mistralai/Mistral-Small-24B-Instruct-2501
|
||||
widget:
|
||||
- messages:
|
||||
- role: user
|
||||
content: What is your favorite condiment?
|
||||
license: other
|
||||
---
|
||||
|
||||
# Model Trained Using AutoTrain
|
||||
|
||||
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
||||
|
||||
# Usage
|
||||
|
||||
```python
|
||||
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_path = "PATH_TO_THIS_REPO"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
device_map="auto",
|
||||
torch_dtype='auto'
|
||||
).eval()
|
||||
|
||||
# Prompt content: "hi"
|
||||
messages = [
|
||||
{"role": "user", "content": "hi"}
|
||||
]
|
||||
|
||||
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
||||
output_ids = model.generate(input_ids.to('cuda'))
|
||||
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
||||
|
||||
# Model response: "Hello! How can I assist you today?"
|
||||
print(response)
|
||||
```
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-Small-24B-Instruct-2501",
|
||||
"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,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 100000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.48.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"temperature": 0.15,
|
||||
"transformers_version": "4.48.0"
|
||||
}
|
||||
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 sha256:550d4063f3657e08936d9ed9985a4239b40bf8aec2dd2b6079efbbb77e8ee0f1
|
||||
size 4781571704
|
||||
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:bc62fe2760d1e98a1eab206a5c015ea2ed4757d85f21b2c7e5881eefa678b257
|
||||
size 4781592744
|
||||
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:db7b012c68076872cae689e0dd31d9a530275debdfafc105c01553552bab997a
|
||||
size 4781592760
|
||||
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:d692ac667bfe6bcfa8b9238962014fa94c6bfe05b6c3f5401dd6ceb5627b3600
|
||||
size 4886471560
|
||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:65a06a6e00eeb682c26143ca519507b7be7a614d17ba53bf95cc02cf5195cf23
|
||||
size 4781592784
|
||||
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:b7ef02448d4b393420fcc1248c0d3e12b00eab6acfd528be19e21dfffb59dc11
|
||||
size 4781592776
|
||||
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:d739c629b3365da7b0974d1cd3f416253b7dde2cc3d0ad7b0594d2004afa8da9
|
||||
size 4886471560
|
||||
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 sha256:9949d884b9a06cbed895dcb69f8a465fa6dbe492bc57e7a6ff529410365e40ee
|
||||
size 4781592784
|
||||
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 sha256:794b29a5f37b6280779c9f82640b8897e6efd966a63fdc07f1e74c97c47ce7bc
|
||||
size 4781592776
|
||||
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 sha256:7ba2809da806140c3518e7cee6b20286e9c83ec0822a35037eb6d4d21f613e0e
|
||||
size 3900777048
|
||||
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"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8bf5f502323acec45b85841697fea20f0e2c648639773b65baa930b68eaec22a
|
||||
size 6710
|
||||
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
|
||||
9020
tokenizer_config.json
Normal file
9020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b5b049561c60e6a852917931724472e9d8291b6975f29b6831f71ba090bbc02
|
||||
size 5688
|
||||
49
training_params.json
Normal file
49
training_params.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"model": "mistralai/Mistral-Small-24B-Instruct-2501",
|
||||
"project_name": "CanisAI-Retriever-1-5",
|
||||
"data_path": "CanisAI-Retriever-1-5/autotrain-data",
|
||||
"train_split": "train",
|
||||
"valid_split": null,
|
||||
"add_eos_token": true,
|
||||
"block_size": 1024,
|
||||
"model_max_length": 2048,
|
||||
"padding": "right",
|
||||
"trainer": "sft",
|
||||
"use_flash_attention_2": false,
|
||||
"log": "tensorboard",
|
||||
"disable_gradient_checkpointing": false,
|
||||
"logging_steps": -1,
|
||||
"eval_strategy": "epoch",
|
||||
"save_total_limit": 1,
|
||||
"auto_find_batch_size": false,
|
||||
"mixed_precision": "fp16",
|
||||
"lr": 3e-05,
|
||||
"epochs": 2,
|
||||
"batch_size": 2,
|
||||
"warmup_ratio": 0.1,
|
||||
"gradient_accumulation": 4,
|
||||
"optimizer": "adamw_torch",
|
||||
"scheduler": "linear",
|
||||
"weight_decay": 0.0,
|
||||
"max_grad_norm": 1.0,
|
||||
"seed": 42,
|
||||
"chat_template": "none",
|
||||
"quantization": "int4",
|
||||
"target_modules": "all-linear",
|
||||
"merge_adapter": true,
|
||||
"peft": true,
|
||||
"lora_r": 16,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.05,
|
||||
"model_ref": null,
|
||||
"dpo_beta": 0.1,
|
||||
"max_prompt_length": 128,
|
||||
"max_completion_length": null,
|
||||
"prompt_text_column": "autotrain_prompt",
|
||||
"text_column": "autotrain_text",
|
||||
"rejected_text_column": "autotrain_rejected_text",
|
||||
"push_to_hub": true,
|
||||
"username": "CanisAI1",
|
||||
"unsloth": true,
|
||||
"distributed_backend": "ddp"
|
||||
}
|
||||
Reference in New Issue
Block a user