Total runs:
4.7M
Run Growth:
-124.2K
Growth Rate:
-2.66%
Sponsored by
APIMart
dphn / dolphin-2.9-llama3-8b-gguf
Model's Last Updated: May 20 2024
Introduction of dolphin-2.9-llama3-8b-gguf
Model Details of dolphin-2.9-llama3-8b-gguf
Dolphin 2.9 Llama 3 8b 🐬
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
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|>"
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 dphn dolphin-2.9-llama3-8b-gguf on huggingface.co
6.3K
Total runs
-40
24-hour runs
193
3-day runs
73
7-day runs
37
30-day runs
More Information About dolphin-2.9-llama3-8b-gguf huggingface.co Model
Url of dolphin-2.9-llama3-8b-gguf
dolphin-2.9-llama3-8b-gguf huggingface.co Url
Provider of dolphin-2.9-llama3-8b-gguf huggingface.co
Other API from dphn
Updated:September 08 2025
Total runs:
36.3K
Run Growth:
-6.5K
Growth Rate:
-18.01%
Total runs:
10.9K
Run Growth:
10.1K
Growth Rate:
93.07%
Total runs:
10.1K
Run Growth:
1.1K
Growth Rate:
11.13%
Total runs:
8.9K
Run Growth:
90
Growth Rate:
1.02%
Total runs:
8.8K
Run Growth:
221
Growth Rate:
2.52%
Total runs:
8.7K
Run Growth:
86
Growth Rate:
0.99%
Total runs:
8.7K
Run Growth:
141
Growth Rate:
1.62%
Total runs:
8.7K
Run Growth:
79
Growth Rate:
0.91%
Total runs:
8.7K
Run Growth:
15
Growth Rate:
0.17%
Total runs:
8.6K
Run Growth:
120
Growth Rate:
1.40%
Total runs:
7.9K
Run Growth:
4.9K
Growth Rate:
62.37%
Total runs:
7.9K
Run Growth:
-462.5K
Growth Rate:
-5885.84%
Total runs:
7.4K
Run Growth:
775
Growth Rate:
10.45%
Total runs:
4.6K
Run Growth:
-84.6K
Growth Rate:
-1838.86%
Total runs:
4.1K
Run Growth:
362
Growth Rate:
8.77%
Total runs:
3.6K
Run Growth:
-78
Growth Rate:
-2.18%
Total runs:
3.5K
Run Growth:
-1.0K
Growth Rate:
-28.90%
Total runs:
2.8K
Run Growth:
-753
Growth Rate:
-26.62%
Total runs:
2.7K
Run Growth:
1.5K
Growth Rate:
57.03%
Total runs:
2.5K
Run Growth:
1.7K
Growth Rate:
69.52%
Total runs:
2.0K
Run Growth:
1.3K
Growth Rate:
65.15%
Total runs:
1.7K
Run Growth:
592
Growth Rate:
35.32%
Total runs:
1.6K
Run Growth:
570
Growth Rate:
35.94%
Total runs:
1.3K
Run Growth:
133
Growth Rate:
10.40%
Total runs:
1.2K
Run Growth:
368
Growth Rate:
30.36%
Total runs:
1.0K
Run Growth:
137
Growth Rate:
13.30%
Total runs:
976
Run Growth:
368
Growth Rate:
37.70%
Total runs:
783
Run Growth:
-110
Growth Rate:
-14.05%
Total runs:
718
Run Growth:
-795
Growth Rate:
-110.72%
Total runs:
631
Run Growth:
-369
Growth Rate:
-58.48%
Total runs:
511
Run Growth:
-19
Growth Rate:
-3.72%
Total runs:
434
Run Growth:
-332
Growth Rate:
-76.50%
Total runs:
421
Run Growth:
-349
Growth Rate:
-82.90%
Total runs:
317
Run Growth:
141
Growth Rate:
44.48%
Total runs:
278
Run Growth:
-150
Growth Rate:
-53.96%
Total runs:
273
Run Growth:
-346
Growth Rate:
-126.74%
Total runs:
267
Run Growth:
167
Growth Rate:
62.55%
Total runs:
246
Run Growth:
-17
Growth Rate:
-6.91%
Total runs:
224
Run Growth:
-119
Growth Rate:
-53.13%
Total runs:
223
Run Growth:
122
Growth Rate:
54.71%
Total runs:
215
Run Growth:
114
Growth Rate:
53.02%
Total runs:
211
Run Growth:
-223
Growth Rate:
-105.69%
Total runs:
192
Run Growth:
-515
Growth Rate:
-268.23%
Total runs:
182
Run Growth:
110
Growth Rate:
60.44%
Total runs:
167
Run Growth:
-38
Growth Rate:
-22.75%
Total runs:
157
Run Growth:
82
Growth Rate:
52.23%
Total runs:
125
Run Growth:
-82
Growth Rate:
-65.60%
Total runs:
107
Run Growth:
-69
Growth Rate:
-64.49%
Total runs:
68
Run Growth:
47
Growth Rate:
69.12%
Total runs:
67
Run Growth:
-6
Growth Rate:
-8.96%
Total runs:
58
Run Growth:
30
Growth Rate:
51.72%
Total runs:
49
Run Growth:
-54
Growth Rate:
-110.20%
Total runs:
44
Run Growth:
-24
Growth Rate:
-54.55%
Total runs:
43
Run Growth:
-29
Growth Rate:
-67.44%
Total runs:
43
Run Growth:
7
Growth Rate:
16.28%
Total runs:
36
Run Growth:
-25
Growth Rate:
-69.44%
Total runs:
35
Run Growth:
-16
Growth Rate:
-45.71%
Total runs:
32
Run Growth:
-39
Growth Rate:
-121.88%
Total runs:
23
Run Growth:
-5
Growth Rate:
-21.74%
Total runs:
22
Run Growth:
5
Growth Rate:
22.73%
Total runs:
21
Run Growth:
-5
Growth Rate:
-23.81%
Total runs:
19
Run Growth:
1
Growth Rate:
5.26%
Total runs:
15
Run Growth:
-4
Growth Rate:
-26.67%
Total runs:
5
Run Growth:
4
Growth Rate:
80.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%