Hugging Face's logo

RichardErkhov
/
mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf

GGUF
conversational
Model card Files
xet
Community
RichardErkhov commited on
Commit
e84dbb0
·
verified ·
1 Parent(s): fc18cd6

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ llama3-1_8b_oh_v3.1_wo_evolinstruct - GGUF
11
+ - Model creator: https://huggingface.co/mlfoundations-dev/
12
+ - Original model: https://huggingface.co/mlfoundations-dev/llama3-1_8b_oh_v3.1_wo_evolinstruct/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [llama3-1_8b_oh_v3.1_wo_evolinstruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama3-1_8b_oh_v3.1_wo_evolinstruct-gguf/blob/main/llama3-1_8b_oh_v3.1_wo_evolinstruct.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ library_name: transformers
46
+ license: llama3.1
47
+ base_model: meta-llama/Meta-Llama-3.1-8B
48
+ tags:
49
+ - llama-factory
50
+ - full
51
+ - generated_from_trainer
52
+ model-index:
53
+ - name: llama3-1_8b_oh_v3.1_wo_evolinstruct
54
+ results: []
55
+ ---
56
+
57
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
58
+ should probably proofread and complete it, then remove this comment. -->
59
+
60
+ # llama3-1_8b_oh_v3.1_wo_evolinstruct
61
+
62
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v3.1_wo_evolinstruct dataset.
63
+ It achieves the following results on the evaluation set:
64
+ - Loss: 0.6348
65
+
66
+ ## Model description
67
+
68
+ More information needed
69
+
70
+ ## Intended uses & limitations
71
+
72
+ More information needed
73
+
74
+ ## Training and evaluation data
75
+
76
+ More information needed
77
+
78
+ ## Training procedure
79
+
80
+ ### Training hyperparameters
81
+
82
+ The following hyperparameters were used during training:
83
+ - learning_rate: 5e-06
84
+ - train_batch_size: 16
85
+ - eval_batch_size: 8
86
+ - seed: 42
87
+ - distributed_type: multi-GPU
88
+ - num_devices: 32
89
+ - total_train_batch_size: 512
90
+ - total_eval_batch_size: 256
91
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
92
+ - lr_scheduler_type: constant
93
+ - lr_scheduler_warmup_ratio: 0.1
94
+ - lr_scheduler_warmup_steps: 1738
95
+ - num_epochs: 3.0
96
+
97
+ ### Training results
98
+
99
+ | Training Loss | Epoch | Step | Validation Loss |
100
+ |:-------------:|:-----:|:----:|:---------------:|
101
+ | 0.6452 | 1.0 | 391 | 0.6435 |
102
+ | 0.5983 | 2.0 | 782 | 0.6336 |
103
+ | 0.5549 | 3.0 | 1173 | 0.6348 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.46.1
109
+ - Pytorch 2.4.0
110
+ - Datasets 3.0.2
111
+ - Tokenizers 0.20.3
112
+
113
+