Hugging Face's logo

RichardErkhov
/
inflatebot_-_L3-8B-Helium3-baseLlama-gguf

GGUF
Inference Endpoints
Model card Files Community
RichardErkhov commited on
Commit
e35e7f1
•
1 Parent(s): a5d9a8b

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ L3-8B-Helium3-baseLlama - GGUF
11
+ - Model creator: https://huggingface.co/inflatebot/
12
+ - Original model: https://huggingface.co/inflatebot/L3-8B-Helium3-baseLlama/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [L3-8B-Helium3-baseLlama.Q2_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [L3-8B-Helium3-baseLlama.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [L3-8B-Helium3-baseLlama.IQ3_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [L3-8B-Helium3-baseLlama.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [L3-8B-Helium3-baseLlama.IQ3_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [L3-8B-Helium3-baseLlama.Q3_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [L3-8B-Helium3-baseLlama.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [L3-8B-Helium3-baseLlama.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [L3-8B-Helium3-baseLlama.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [L3-8B-Helium3-baseLlama.Q4_0.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [L3-8B-Helium3-baseLlama.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [L3-8B-Helium3-baseLlama.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [L3-8B-Helium3-baseLlama.Q4_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [L3-8B-Helium3-baseLlama.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [L3-8B-Helium3-baseLlama.Q4_1.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [L3-8B-Helium3-baseLlama.Q5_0.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [L3-8B-Helium3-baseLlama.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [L3-8B-Helium3-baseLlama.Q5_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [L3-8B-Helium3-baseLlama.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [L3-8B-Helium3-baseLlama.Q5_1.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [L3-8B-Helium3-baseLlama.Q6_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [L3-8B-Helium3-baseLlama.Q8_0.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_L3-8B-Helium3-baseLlama-gguf/blob/main/L3-8B-Helium3-baseLlama.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model:
46
+ - NousResearch/Meta-Llama-3-8B
47
+ - inflatebot/helide-beta-r1
48
+ - inflatebot/helide-beta-r0
49
+ - inflatebot/helide-beta-r4
50
+ library_name: transformers
51
+ tags:
52
+ - mergekit
53
+ - merge
54
+
55
+ ---
56
+ # helium-3-r2
57
+
58
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
59
+
60
+ ## Merge Details
61
+
62
+ Helium3, but the base model is Llama-3. Ended up being too dry, but if He3's too horny for you, try this one.
63
+
64
+ [GGUFs by mradermacher](https://huggingface.co/mradermacher/L3-8B-Helium3-baseLlama-GGUF)
65
+
66
+ ### Merge Method
67
+
68
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
69
+
70
+ ### Models Merged
71
+
72
+ The following models were included in the merge:
73
+ * [inflatebot/helide-beta-r1](https://huggingface.co/inflatebot/helide-beta-r1)
74
+ * [inflatebot/helide-beta-r0](https://huggingface.co/inflatebot/helide-beta-r0)
75
+ * [inflatebot/helide-beta-r4](https://huggingface.co/inflatebot/helide-beta-r4)
76
+
77
+ ### Configuration
78
+
79
+ The following YAML configuration was used to produce this model:
80
+
81
+ ```yaml
82
+ models:
83
+ - model: inflatebot/helide-beta-r4
84
+ - model: inflatebot/helide-beta-r1
85
+ - model: inflatebot/helide-beta-r0
86
+
87
+ merge_method: model_stock
88
+ base_model: NousResearch/Meta-Llama-3-8B
89
+ dtype: bfloat16
90
+
91
+ ```
92
+
93
+