初始化项目，由ModelHub XC社区提供模型
Model: leonvanbokhorst/Llama-3.2-1B-Instruct-Complaint 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
|
||||
14
README.md
Normal file
14
README.md
Normal file
@@ -0,0 +1,14 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- leonvanbokhorst/synthetic-complaints-v2
|
||||
language:
|
||||
- en
|
||||
metrics:
|
||||
- bleu
|
||||
- accuracy
|
||||
base_model:
|
||||
- unsloth/Llama-3.2-1B-Instruct
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
40
config.json
Normal file
40
config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 32.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.47.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.47.0.dev0"
|
||||
}
|
||||
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 sha256:86b8f7b0d158cacc562c9e3693b46910f0b281ff1bb60fbf854514cf66fe6979
|
||||
size 1956695880
|
||||
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 sha256:574e1897038b417ce020398b19ff13068ef39344458d659854b6f4cc1e4a4e1e
|
||||
size 1946296312
|
||||
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 sha256:87aa0108b84b01dd1a01929ba1d27fd175868df82977e59d3e0d291943558f61
|
||||
size 1040282032
|
||||
153
model.safetensors.index.json
Normal file
153
model.safetensors.index.json
Normal file
@@ -0,0 +1,153 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 4943257600
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|finetune_right_pad_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be428aa6426731ece2ddafa5e54e433e7c073a0eba314db0a6e51ebe7c64a916
|
||||
size 17210198
|
||||
2066
tokenizer_config.json
Normal file
2066
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user