Total runs:
421
Run Growth:
386
Growth Rate:
91.69%
Sponsored by
Vmake Labs Video Enhancer
Delta-Vector / Holland-4B-GGUF
Model's Last Updated: December 21 2024
Introduction of Holland-4B-GGUF
Model Details of Holland-4B-GGUF
A model made to continue off my previous work on
Magnum 4B
, A small model made for creative writing / General assistant tasks, finetuned ontop of
IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
, this model is made to be more coherent and generally be better then the 4B at both writing and assistant tasks.
GGUF quants of Holland 4B, Thanks Lucy <3 Original weights can be found here
Prompting
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
Support
To run inference on this model, you'll need to use Aphrodite, vLLM or EXL 2/tabbyAPI, as llama.cpp hasn't yet merged the required pull request to fix the llama 3.1 rope_freqs issue with custom head dimensions.
However, you can work around this by quantizing the model yourself to create a functional GGUF file. Note that until this PR is merged, the context will be limited to 8 k tokens.
To create a working GGUF file, make the following adjustments:
-
Remove the
"rope_scaling": {}entry fromconfig.json -
Change
"max_position_embeddings"to8192inconfig.json
These modifications should allow you to use the model with llama. Cpp, albeit with the mentioned context limitation.
Axolotl config
See axolotl config
Axolotl version:
0.4.1
base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: NewEden/Gryphe-3.5-16k-Subset
type: sharegpt
conversation: chatml
- path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
type: sharegpt
conversation: chatml
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal
type: sharegpt
conversation: chatml
- path: PJMixers/lodrick-the-lafted_OpusStories-ShareGPT
type: sharegpt
conversation: chatml
chat_template: chatml
val_set_size: 0.01
output_dir: ./outputs/out
adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
sequence_len: 16384
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
#optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00002
weight_decay: 0.05
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
#deepspeed:
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>
Credits
- anthracite-org/kalo-opus-instruct-22k-no-refusal
- NewEden/Gryphe-3.5-16k-Subset
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
- lodrick-the-lafted/OpusStories
I couldn't have made this model without the help of Kubernetes_bad and the support of Lucy Knada
Training
The training was done for 2 epochs. We used 2 x RTX 6000s GPUs graciously provided by Kubernetes_Bad for the full-parameter fine-tuning of the model.
Safety
...
Runs of Delta-Vector Holland-4B-GGUF on huggingface.co
34
Total runs
0
24-hour runs
0
3-day runs
-3
7-day runs
6
30-day runs
More Information About Holland-4B-GGUF huggingface.co Model
Url of Holland-4B-GGUF
Holland-4B-GGUF huggingface.co Url
Provider of Holland-4B-GGUF huggingface.co
Other API from Delta-Vector
Updated:September 28 2025
Total runs:
322
Run Growth:
0
Growth Rate:
0.00%
Total runs:
206
Run Growth:
0
Growth Rate:
0.00%
Total runs:
187
Run Growth:
105
Growth Rate:
57.07%
Total runs:
144
Run Growth:
0
Growth Rate:
0.00%
Total runs:
106
Run Growth:
0
Growth Rate:
0.00%
Total runs:
99
Run Growth:
63
Growth Rate:
65.63%
Total runs:
98
Run Growth:
49
Growth Rate:
50.00%
Total runs:
91
Run Growth:
58
Growth Rate:
63.74%
Total runs:
89
Run Growth:
0
Growth Rate:
0.00%
Total runs:
89
Run Growth:
70
Growth Rate:
78.65%
Total runs:
88
Run Growth:
12
Growth Rate:
13.48%
Total runs:
87
Run Growth:
80
Growth Rate:
91.95%
Total runs:
75
Run Growth:
12
Growth Rate:
16.00%
Total runs:
75
Run Growth:
-29
Growth Rate:
-38.67%
Total runs:
74
Run Growth:
0
Growth Rate:
0.00%
Total runs:
68
Run Growth:
0
Growth Rate:
0.00%
Total runs:
64
Run Growth:
13
Growth Rate:
20.31%
Total runs:
64
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:
57
Run Growth:
0
Growth Rate:
0.00%
Total runs:
54
Run Growth:
0
Growth Rate:
0.00%
Total runs:
48
Run Growth:
32
Growth Rate:
66.67%
Total runs:
47
Run Growth:
0
Growth Rate:
0.00%
Total runs:
45
Run Growth:
6
Growth Rate:
13.33%
Total runs:
44
Run Growth:
0
Growth Rate:
0.00%
Total runs:
43
Run Growth:
36
Growth Rate:
83.72%
Total runs:
42
Run Growth:
19
Growth Rate:
45.24%
Total runs:
40
Run Growth:
0
Growth Rate:
0.00%
Total runs:
37
Run Growth:
12
Growth Rate:
32.43%
Total runs:
37
Run Growth:
24
Growth Rate:
66.67%
Total runs:
36
Run Growth:
8
Growth Rate:
22.86%
Total runs:
35
Run Growth:
0
Growth Rate:
0.00%
Total runs:
35
Run Growth:
0
Growth Rate:
0.00%
Total runs:
34
Run Growth:
0
Growth Rate:
0.00%
Total runs:
33
Run Growth:
24
Growth Rate:
72.73%
Total runs:
32
Run Growth:
0
Growth Rate:
0.00%
Total runs:
31
Run Growth:
0
Growth Rate:
0.00%
Total runs:
31
Run Growth:
0
Growth Rate:
0.00%
Total runs:
30
Run Growth:
-18
Growth Rate:
-60.00%
Total runs:
30
Run Growth:
0
Growth Rate:
0.00%
Total runs:
30
Run Growth:
0
Growth Rate:
0.00%
Total runs:
29
Run Growth:
20
Growth Rate:
68.97%
Total runs:
28
Run Growth:
15
Growth Rate:
55.56%
Total runs:
27
Run Growth:
-13
Growth Rate:
-48.15%
Total runs:
27
Run Growth:
9
Growth Rate:
33.33%
Total runs:
26
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
-5
Growth Rate:
-19.23%
Total runs:
26
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
17
Growth Rate:
65.38%
Total runs:
25
Run Growth:
0
Growth Rate:
0.00%
Total runs:
24
Run Growth:
0
Growth Rate:
0.00%
Total runs:
24
Run Growth:
17
Growth Rate:
70.83%
Total runs:
24
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
17
Growth Rate:
73.91%
Total runs:
23
Run Growth:
-133
Growth Rate:
-578.26%
Total runs:
23
Run Growth:
15
Growth Rate:
68.18%
Total runs:
22
Run Growth:
0
Growth Rate:
0.00%
Total runs:
22
Run Growth:
0
Growth Rate:
0.00%
Total runs:
22
Run Growth:
0
Growth Rate:
0.00%
Total runs:
22
Run Growth:
0
Growth Rate:
0.00%
Total runs:
22
Run Growth:
-19
Growth Rate:
-86.36%
Total runs:
22
Run Growth:
13
Growth Rate:
59.09%
Total runs:
22
Run Growth:
12
Growth Rate:
54.55%
Total runs:
21
Run Growth:
15
Growth Rate:
78.95%
Total runs:
21
Run Growth:
0
Growth Rate:
0.00%
Total runs:
20
Run Growth:
13
Growth Rate:
65.00%
Total runs:
20
Run Growth:
7
Growth Rate:
35.00%
Total runs:
20
Run Growth:
0
Growth Rate:
0.00%
Total runs:
20
Run Growth:
8
Growth Rate:
40.00%