Model save
Browse files- README.md +61 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Oct11_16-27-09_18e880f38d3e/events.out.tfevents.1728664032.18e880f38d3e.95.0 +3 -0
- runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728670957.18e880f38d3e.42189.0 +3 -0
- runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728674350.18e880f38d3e.42189.1 +3 -0
- runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728674684.18e880f38d3e.42189.2 +3 -0
- runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728675239.18e880f38d3e.42189.3 +3 -0
- runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728675848.18e880f38d3e.42189.4 +3 -0
- special_tokens_map.json +40 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +88 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/codellama-7b-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- unsloth
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: CodeLlama-7b-hf
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# CodeLlama-7b-hf
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [unsloth/codellama-7b-bnb-4bit](https://huggingface.co/unsloth/codellama-7b-bnb-4bit) on the None dataset.
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0002
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 3407
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 10
|
| 48 |
+
- training_steps: 120
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.13.2
|
| 58 |
+
- Transformers 4.44.2
|
| 59 |
+
- Pytorch 2.4.1+cu121
|
| 60 |
+
- Datasets 3.0.1
|
| 61 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/codellama-7b-bnb-4bit",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be4a3e0aa1a07c4e20115fab01fe7e2cd2bac0373409455d965e8efc05c122c9
|
| 3 |
+
size 159967880
|
runs/Oct11_16-27-09_18e880f38d3e/events.out.tfevents.1728664032.18e880f38d3e.95.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5ad25ccd084696cb78df76e0e6cbb70ddecee0ec0e18bf5f4d7521e8643600e
|
| 3 |
+
size 30960
|
runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728670957.18e880f38d3e.42189.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfd44ab80e9eceeab9ccffa0edd6d59f5ddc92f16f58ace363490ca006cfb4f4
|
| 3 |
+
size 30960
|
runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728674350.18e880f38d3e.42189.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6b98bea875fdee77c1b156f7432ca8d28c952cb453f8536cd795d7a884ea8c
|
| 3 |
+
size 30960
|
runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728674684.18e880f38d3e.42189.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de78e43d800f0da935614ff1e0f8bff24f6b36abb4c154e198e8901a86470768
|
| 3 |
+
size 30960
|
runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728675239.18e880f38d3e.42189.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587dfb234ac7c9518a8918631a371a40a8ce6ce66f85f003a151234697a86a98
|
| 3 |
+
size 36851
|
runs/Oct11_18-20-44_18e880f38d3e/events.out.tfevents.1728675848.18e880f38d3e.42189.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:496fc4d73ac9213e7d56fa94ab69525ab27f08cf520612008a806b4a347a5800
|
| 3 |
+
size 30960
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"β<PRE>",
|
| 4 |
+
"β<MID>",
|
| 5 |
+
"β<SUF>",
|
| 6 |
+
"β<EOT>",
|
| 7 |
+
"β<PRE>",
|
| 8 |
+
"β<MID>",
|
| 9 |
+
"β<SUF>",
|
| 10 |
+
"β<EOT>"
|
| 11 |
+
],
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"pad_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"unk_token": {
|
| 34 |
+
"content": "<unk>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
| 3 |
+
size 500058
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32007": {
|
| 30 |
+
"content": "β<PRE>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32008": {
|
| 38 |
+
"content": "β<SUF>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32009": {
|
| 46 |
+
"content": "β<MID>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32010": {
|
| 54 |
+
"content": "β<EOT>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"additional_special_tokens": [
|
| 63 |
+
"β<PRE>",
|
| 64 |
+
"β<MID>",
|
| 65 |
+
"β<SUF>",
|
| 66 |
+
"β<EOT>",
|
| 67 |
+
"β<PRE>",
|
| 68 |
+
"β<MID>",
|
| 69 |
+
"β<SUF>",
|
| 70 |
+
"β<EOT>"
|
| 71 |
+
],
|
| 72 |
+
"bos_token": "<s>",
|
| 73 |
+
"clean_up_tokenization_spaces": false,
|
| 74 |
+
"eos_token": "</s>",
|
| 75 |
+
"eot_token": "β<EOT>",
|
| 76 |
+
"fill_token": "<FILL_ME>",
|
| 77 |
+
"legacy": null,
|
| 78 |
+
"middle_token": "β<MID>",
|
| 79 |
+
"model_max_length": 16384,
|
| 80 |
+
"pad_token": "<unk>",
|
| 81 |
+
"padding_side": "right",
|
| 82 |
+
"prefix_token": "β<PRE>",
|
| 83 |
+
"sp_model_kwargs": {},
|
| 84 |
+
"suffix_token": "β<SUF>",
|
| 85 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
| 86 |
+
"unk_token": "<unk>",
|
| 87 |
+
"use_default_system_prompt": false
|
| 88 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b874700ebb3583916be5ecea3b30c66b8bf810c93b5f42ad9325169a4f4490
|
| 3 |
+
size 5496
|