Update README.md
Browse files
README.md
CHANGED
@@ -46,6 +46,103 @@ To create a working GGUF file, make the following adjustments:
|
|
46 |
|
47 |
These modifications should allow you to use the model with llama.cpp, albeit with the mentioned context limitation.
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
## Credits
|
50 |
|
51 |
- [anthracite-org/Stheno-Data-Filtered](https://huggingface.co/datasets/anthracite-org/Stheno-Data-Filtered)
|
|
|
46 |
|
47 |
These modifications should allow you to use the model with llama.cpp, albeit with the mentioned context limitation.
|
48 |
|
49 |
+
## axolotl config
|
50 |
+
|
51 |
+
<details><summary>See axolotl config</summary>
|
52 |
+
|
53 |
+
axolotl version: `0.4.1`
|
54 |
+
```yaml
|
55 |
+
base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
|
56 |
+
model_type: AutoModelForCausalLM
|
57 |
+
tokenizer_type: AutoTokenizer
|
58 |
+
|
59 |
+
load_in_8bit: false
|
60 |
+
load_in_4bit: false
|
61 |
+
strict: false
|
62 |
+
|
63 |
+
datasets:
|
64 |
+
- path: anthracite-org/Gryphe-3.5-16k-Subset
|
65 |
+
type: sharegpt
|
66 |
+
conversation: chatml
|
67 |
+
- path: Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned
|
68 |
+
type: sharegpt
|
69 |
+
conversation: chatml
|
70 |
+
- path: anthracite-org/Stheno-Data-Filtered
|
71 |
+
type: sharegpt
|
72 |
+
conversation: chatml
|
73 |
+
- path: Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned
|
74 |
+
type: sharegpt
|
75 |
+
conversation: chatml
|
76 |
+
- path: lodrick-the-lafted/NopmWritingStruct
|
77 |
+
type: sharegpt
|
78 |
+
conversation: chatml
|
79 |
+
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal
|
80 |
+
type: sharegpt
|
81 |
+
conversation: chatml
|
82 |
+
|
83 |
+
chat_template: chatml
|
84 |
+
|
85 |
+
val_set_size: 0.01
|
86 |
+
output_dir: ./outputs/out
|
87 |
+
|
88 |
+
adapter:
|
89 |
+
lora_r:
|
90 |
+
lora_alpha:
|
91 |
+
lora_dropout:
|
92 |
+
lora_target_linear:
|
93 |
+
|
94 |
+
sequence_len: 16384
|
95 |
+
# sequence_len: 32768
|
96 |
+
sample_packing: true
|
97 |
+
eval_sample_packing: false
|
98 |
+
pad_to_sequence_len: true
|
99 |
+
|
100 |
+
wandb_project:
|
101 |
+
wandb_entity:
|
102 |
+
wandb_watch:
|
103 |
+
wandb_name:
|
104 |
+
wandb_log_model:
|
105 |
+
|
106 |
+
gradient_accumulation_steps: 32
|
107 |
+
micro_batch_size: 1
|
108 |
+
num_epochs: 2
|
109 |
+
optimizer: adamw_bnb_8bit
|
110 |
+
lr_scheduler: cosine
|
111 |
+
learning_rate: 0.00002
|
112 |
+
weight_decay: 0.05
|
113 |
+
|
114 |
+
train_on_inputs: false
|
115 |
+
group_by_length: false
|
116 |
+
bf16: auto
|
117 |
+
fp16:
|
118 |
+
tf32: true
|
119 |
+
|
120 |
+
gradient_checkpointing: true
|
121 |
+
early_stopping_patience:
|
122 |
+
resume_from_checkpoint:
|
123 |
+
local_rank:
|
124 |
+
logging_steps: 1
|
125 |
+
xformers_attention:
|
126 |
+
flash_attention: true
|
127 |
+
|
128 |
+
warmup_ratio: 0.1
|
129 |
+
evals_per_epoch: 4
|
130 |
+
eval_table_size:
|
131 |
+
eval_max_new_tokens: 128
|
132 |
+
saves_per_epoch: 1
|
133 |
+
|
134 |
+
debug:
|
135 |
+
deepspeed:
|
136 |
+
fsdp:
|
137 |
+
fsdp_config:
|
138 |
+
|
139 |
+
special_tokens:
|
140 |
+
pad_token: <|finetune_right_pad_id|>
|
141 |
+
|
142 |
+
```
|
143 |
+
|
144 |
+
</details><br>
|
145 |
+
|
146 |
## Credits
|
147 |
|
148 |
- [anthracite-org/Stheno-Data-Filtered](https://huggingface.co/datasets/anthracite-org/Stheno-Data-Filtered)
|