Total runs:
4.8M
Run Growth:
0
Growth Rate:
0.00%
Sponsored by
PoYo.AI
cognitivecomputations / dolphin-2.9-llama3-8b-1m
Model's Last Updated: May 20 2024
text-generation
Introduction of dolphin-2.9-llama3-8b-1m
Model Details of dolphin-2.9-llama3-8b-1m
Dolphin 2.9 Llama 3 8b 1m 🐬
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
This version of Dolphin has a 1 million token context. I have applied
winglian/llama-3-1m-context-gradient-lora
- created by @gradientai and @winglian and sponsored by @CrusoeCloud
A bug has been found in the Dolphin 2.9 dataset in SystemConversations that causes the model to overly talk about the "SYSTEM MESSAGE". To counter this, we recommend you add a statement in the system message directing the model not to mention the system message. An example system message is "The assistant is named Dolphin. A helpful and friendly AI assistant, Dolphin avoids discussing the system message unless directly asked about it."
My appreciation for the sponsors of Dolphin 2.9:
- Crusoe Cloud - provided excellent on-demand 10xL40S node
This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT
The base model has 8k context, and the full-weight fine-tuning was with 4k sequence length.
It took 2.5 days on 8x L40S provided by Crusoe Cloud
This model was trained FFT on all parameters, using ChatML prompt template format.
example:
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
Dolphin is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.
See axolotl config
axolotl version:
0.4.0
base_model: meta-llama/Meta-Llama-3-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false
load_in_8bit: false
load_in_4bit: false
strict: false
model_config:
datasets:
- path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/Ultrachat200kunfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/SystemConversations.jsonl
type: sharegpt
conversation: chatml
chat_template: chatml
dataset_prepared_path: /workspace/datasets/dolphin-2.9/thingy
val_set_size: 0.0002
output_dir: ./out
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
gradient_accumulation_steps: 4
micro_batch_size: 3
num_epochs: 3
logging_steps: 1
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
wandb_project: dolphin-2.9-mixtral-8x22b
wandb_watch:
wandb_run_id:
wandb_log_model:
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 4
save_total_limit: 2
save_steps:
evals_per_epoch: 4
eval_sample_packing: false
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<|end_of_text|>"
tokens:
- "<|im_start|>"
- "<|im_end|>"
Quants
GGUF : https://huggingface.co/QuantFactory/dolphin-2.9-llama3-8b-GGUF
GGUF with imatrix: https://huggingface.co/bartowski/dolphin-2.9-llama3-8b-GGUF
Exllamav2: https://huggingface.co/bartowski/dolphin-2.9-llama3-8b-exl2
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 7
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.146 | 0.0005 | 1 | 1.1064 |
| 0.6962 | 0.2501 | 555 | 0.6636 |
| 0.6857 | 0.5001 | 1110 | 0.6503 |
| 0.6592 | 0.7502 | 1665 | 0.6419 |
| 0.6465 | 1.0002 | 2220 | 0.6317 |
| 0.5295 | 1.2395 | 2775 | 0.6408 |
| 0.5302 | 1.4895 | 3330 | 0.6351 |
| 0.5188 | 1.7396 | 3885 | 0.6227 |
| 0.521 | 1.9896 | 4440 | 0.6168 |
| 0.3968 | 2.2289 | 4995 | 0.6646 |
| 0.3776 | 2.4789 | 5550 | 0.6619 |
| 0.3983 | 2.7290 | 6105 | 0.6602 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
Runs of cognitivecomputations dolphin-2.9-llama3-8b-1m on huggingface.co
30
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About dolphin-2.9-llama3-8b-1m huggingface.co Model
Url of dolphin-2.9-llama3-8b-1m
dolphin-2.9-llama3-8b-1m huggingface.co Url
Provider of dolphin-2.9-llama3-8b-1m huggingface.co
Other API from cognitivecomputations
Updated:May 20 2024
Total runs:
35.9K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12.9K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12.4K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
11.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
10.4K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
10.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8.9K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
6.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
5.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
5.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3.2K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.6K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.4K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.4K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.2K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.2K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.2K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.9K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.7K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.7K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.5K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.4K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.2K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.2K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
993
Run Growth:
0
Growth Rate:
0.00%
Total runs:
982
Run Growth:
0
Growth Rate:
0.00%
Total runs:
960
Run Growth:
0
Growth Rate:
0.00%
Total runs:
951
Run Growth:
0
Growth Rate:
0.00%
Total runs:
933
Run Growth:
0
Growth Rate:
0.00%
Total runs:
810
Run Growth:
0
Growth Rate:
0.00%
Total runs:
795
Run Growth:
0
Growth Rate:
0.00%
Total runs:
788
Run Growth:
0
Growth Rate:
0.00%
Total runs:
716
Run Growth:
0
Growth Rate:
0.00%
Total runs:
461
Run Growth:
0
Growth Rate:
0.00%
Total runs:
456
Run Growth:
0
Growth Rate:
0.00%
Total runs:
447
Run Growth:
0
Growth Rate:
0.00%
Total runs:
385
Run Growth:
0
Growth Rate:
0.00%
Total runs:
309
Run Growth:
0
Growth Rate:
0.00%
Total runs:
223
Run Growth:
0
Growth Rate:
0.00%
Total runs:
219
Run Growth:
0
Growth Rate:
0.00%
Total runs:
210
Run Growth:
0
Growth Rate:
0.00%
Total runs:
198
Run Growth:
0
Growth Rate:
0.00%
Total runs:
186
Run Growth:
0
Growth Rate:
0.00%
Total runs:
155
Run Growth:
0
Growth Rate:
0.00%
Total runs:
153
Run Growth:
0
Growth Rate:
0.00%
Total runs:
144
Run Growth:
0
Growth Rate:
0.00%
Total runs:
113
Run Growth:
0
Growth Rate:
0.00%
Total runs:
112
Run Growth:
0
Growth Rate:
0.00%
Total runs:
108
Run Growth:
0
Growth Rate:
0.00%
Total runs:
101
Run Growth:
0
Growth Rate:
0.00%
Total runs:
90
Run Growth:
0
Growth Rate:
0.00%
Total runs:
84
Run Growth:
0
Growth Rate:
0.00%
Total runs:
81
Run Growth:
0
Growth Rate:
0.00%
Total runs:
78
Run Growth:
0
Growth Rate:
0.00%
Total runs:
77
Run Growth:
0
Growth Rate:
0.00%
Total runs:
61
Run Growth:
0
Growth Rate:
0.00%
Total runs:
57
Run Growth:
0
Growth Rate:
0.00%
Total runs:
43
Run Growth:
0
Growth Rate:
0.00%
Total runs:
40
Run Growth:
0
Growth Rate:
0.00%
Total runs:
38
Run Growth:
0
Growth Rate:
0.00%
Total runs:
34
Run Growth:
0
Growth Rate:
0.00%
Total runs:
33
Run Growth:
0
Growth Rate:
0.00%
Total runs:
29
Run Growth:
0
Growth Rate:
0.00%
Total runs:
28
Run Growth:
0
Growth Rate:
0.00%