Hugging Face's logo

afrideva
/
Astrohermes-3B-GGUF

Text Generation
Transformers
GGUF
English
gpt
llm
stablelm
ggml
quantized
q2_k
q3_k_m
q4_k_m
q5_k_m
q6_k
q8_0
Model card Files Community
afrideva commited on
Commit
2ab5717
•
1 Parent(s): ab00e49

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Aryanne/Astrohermes-3B
3
+ inference: false
4
+ language:
5
+ - en
6
+ library_name: transformers
7
+ license: cc-by-sa-4.0
8
+ model_creator: Aryanne
9
+ model_name: Astrohermes-3B
10
+ pipeline_tag: text-generation
11
+ quantized_by: afrideva
12
+ tags:
13
+ - gpt
14
+ - llm
15
+ - stablelm
16
+ - gguf
17
+ - ggml
18
+ - quantized
19
+ - q2_k
20
+ - q3_k_m
21
+ - q4_k_m
22
+ - q5_k_m
23
+ - q6_k
24
+ - q8_0
25
+ ---
26
+ # Aryanne/Astrohermes-3B-GGUF
27
+
28
+ Quantized GGUF model files for [Astrohermes-3B](https://huggingface.co/Aryanne/Astrohermes-3B) from [Aryanne](https://huggingface.co/Aryanne)
29
+
30
+
31
+ | Name | Quant method | Size |
32
+ | ---- | ---- | ---- |
33
+ | [astrohermes-3b.fp16.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.fp16.gguf) | fp16 | 5.59 GB |
34
+ | [astrohermes-3b.q2_k.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.q2_k.gguf) | q2_k | 1.20 GB |
35
+ | [astrohermes-3b.q3_k_m.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.q3_k_m.gguf) | q3_k_m | 1.39 GB |
36
+ | [astrohermes-3b.q4_k_m.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.q4_k_m.gguf) | q4_k_m | 1.71 GB |
37
+ | [astrohermes-3b.q5_k_m.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.q5_k_m.gguf) | q5_k_m | 1.99 GB |
38
+ | [astrohermes-3b.q6_k.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.q6_k.gguf) | q6_k | 2.30 GB |
39
+ | [astrohermes-3b.q8_0.gguf](https://huggingface.co/afrideva/Astrohermes-3B-GGUF/resolve/main/astrohermes-3b.q8_0.gguf) | q8_0 | 2.97 GB |
40
+
41
+
42
+
43
+ ## Original Model Card:
44
+ This model is a mix of [PAIXAI/Astrid-3B](https://huggingface.co/PAIXAI/Astrid-3B) + [jondurbin/airoboros-3b-3p0](https://huggingface.co/jondurbin/airoboros-3b-3p0) + [cxllin/StableHermes-3b](https://huggingface.co/cxllin/StableHermes-3b), as shown in the yaml(see Astrohermes.yml or below).
45
+ [Aryanne/Astridboros-3B](https://huggingface.co/Aryanne/Astridboros-3B) = PAIXAI/Astrid-3B + jondurbin/airoboros-3b-3p0
46
+
47
+ ```yaml
48
+ slices:
49
+ - sources:
50
+ - model: Aryanne/Astridboros-3B
51
+ layer_range: [0, 15]
52
+ - sources:
53
+ - model: cxllin/StableHermes-3b
54
+ layer_range: [15, 16]
55
+ - sources:
56
+ - model: Aryanne/Astridboros-3B
57
+ layer_range: [16, 17]
58
+ - sources:
59
+ - model: cxllin/StableHermes-3b
60
+ layer_range: [17, 18]
61
+ - sources:
62
+ - model: Aryanne/Astridboros-3B
63
+ layer_range: [18, 19]
64
+ - sources:
65
+ - model: cxllin/StableHermes-3b
66
+ layer_range: [19, 20]
67
+ - sources:
68
+ - model: Aryanne/Astridboros-3B
69
+ layer_range: [20, 21]
70
+ - sources:
71
+ - model: cxllin/StableHermes-3b
72
+ layer_range: [21, 22]
73
+ - sources:
74
+ - model: Aryanne/Astridboros-3B
75
+ layer_range: [22, 23]
76
+ - sources:
77
+ - model: cxllin/StableHermes-3b
78
+ layer_range: [23, 24]
79
+ - sources:
80
+ - model: Aryanne/Astridboros-3B
81
+ layer_range: [24, 32]
82
+ merge_method: passthrough
83
+ dtype: float16
84
+
85
+ ```