Hugging Face's logo

bartowski
/
Hyperion-3.0-Mistral-7B-alpha-GGUF

Text Generation
Transformers
GGUF
English
code
chemistry
medical
Inference Endpoints
Model card Files Community
1
bartowski commited on
Commit
dcf9f09
•
1 Parent(s): eb54043

Llamacpp quants

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. Hyperion-3.0-Mistral-7B-alpha-Q2_K.gguf +3 -0
  3. Hyperion-3.0-Mistral-7B-alpha-Q3_K_L.gguf +3 -0
  4. Hyperion-3.0-Mistral-7B-alpha-Q3_K_M.gguf +3 -0
  5. Hyperion-3.0-Mistral-7B-alpha-Q3_K_S.gguf +3 -0
  6. Hyperion-3.0-Mistral-7B-alpha-Q4_0.gguf +3 -0
  7. Hyperion-3.0-Mistral-7B-alpha-Q4_K_M.gguf +3 -0
  8. Hyperion-3.0-Mistral-7B-alpha-Q4_K_S.gguf +3 -0
  9. Hyperion-3.0-Mistral-7B-alpha-Q5_0.gguf +3 -0
  10. Hyperion-3.0-Mistral-7B-alpha-Q5_K_M.gguf +3 -0
  11. Hyperion-3.0-Mistral-7B-alpha-Q5_K_S.gguf +3 -0
  12. Hyperion-3.0-Mistral-7B-alpha-Q6_K.gguf +3 -0
  13. Hyperion-3.0-Mistral-7B-alpha-Q8_0.gguf +3 -0
  14. README.md +39 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Hyperion-3.0-Mistral-7B-alpha-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Hyperion-3.0-Mistral-7B-alpha-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Hyperion-3.0-Mistral-7B-alpha-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Hyperion-3.0-Mistral-7B-alpha-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Hyperion-3.0-Mistral-7B-alpha-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Hyperion-3.0-Mistral-7B-alpha-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Hyperion-3.0-Mistral-7B-alpha-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Hyperion-3.0-Mistral-7B-alpha-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Hyperion-3.0-Mistral-7B-alpha-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Hyperion-3.0-Mistral-7B-alpha-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Hyperion-3.0-Mistral-7B-alpha-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Hyperion-3.0-Mistral-7B-alpha-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Hyperion-3.0-Mistral-7B-alpha-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95414158be324ae2027ab2b23626a996272a17f2f6158b8f9505b765a23dae0
3
+ size 2719242016
Hyperion-3.0-Mistral-7B-alpha-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e81ef427f0ffbdb1ad2f50eca0dabbe084171cda1b17d1bbf0440a8404de21c
3
+ size 3822024480
Hyperion-3.0-Mistral-7B-alpha-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f46b4c30050fbce0739e4a74cf142d02015be80b1d6933df61dcdf58e9d16e8
3
+ size 3518986016
Hyperion-3.0-Mistral-7B-alpha-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d0262c461b18e7414a3a34802d66f92e414f2f5b107c7eb5a3c450643ac6c3
3
+ size 3164567328
Hyperion-3.0-Mistral-7B-alpha-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d064a7213b12d7ea748059972b5147d3bc27a47be2add0e0b6794ee433b600
3
+ size 4108916512
Hyperion-3.0-Mistral-7B-alpha-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b38d6b67e17cfa68101676d036c0ca820d828d3c3cd365616e29fa1b8f7de6b
3
+ size 4368439072
Hyperion-3.0-Mistral-7B-alpha-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498f6b52aaebc2ac3276d98cdf23f700885a0a8e3794cbea87e7aadfd60e6728
3
+ size 4140373792
Hyperion-3.0-Mistral-7B-alpha-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28b234717bc24dd459e0dd866a37ca1bbe09e22c68f8e434269009e650d9eda
3
+ size 4997715744
Hyperion-3.0-Mistral-7B-alpha-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4275ae963c25a95d14d760c5187c68d2f634393c931c0999b58af73670bed49
3
+ size 5131409184
Hyperion-3.0-Mistral-7B-alpha-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c4570a6de9feea3093b485a96561844316fe3b96365c4ea6bb62f30c64efef
3
+ size 4997715744
Hyperion-3.0-Mistral-7B-alpha-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6d027d9ee148b378540f1dbc56344536c2eafd356b3bc0d7457d3d5dd986ea
3
+ size 5942064928
Hyperion-3.0-Mistral-7B-alpha-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8da4758d41c785aa0b687f4b910c5e603d9dcbdd0a91fb6a36f50ee051ed27
3
+ size 7695857440
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - code
5
+ - chemistry
6
+ - medical
7
+ license: apache-2.0
8
+ datasets:
9
+ - Locutusque/hyperion-v3.0
10
+ language:
11
+ - en
12
+ quantized_by: bartowski
13
+ pipeline_tag: text-generation
14
+ ---
15
+
16
+ ## Llamacpp Quantizations of Hyperion-3.0-Mistral-7B-alpha
17
+
18
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
19
+
20
+ Original model: https://huggingface.co/Locutusque/Hyperion-3.0-Mistral-7B-alpha
21
+
22
+ Download a file (not the whole branch) from below:
23
+
24
+ | Filename | Quant type | File Size | Description |
25
+ | -------- | ---------- | --------- | ----------- |
26
+ | [Hyperion-3.0-Mistral-7B-alpha-Q8_0.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
27
+ | [Hyperion-3.0-Mistral-7B-alpha-Q6_K.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
28
+ | [Hyperion-3.0-Mistral-7B-alpha-Q5_K_M.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
29
+ | [Hyperion-3.0-Mistral-7B-alpha-Q5_K_S.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
30
+ | [Hyperion-3.0-Mistral-7B-alpha-Q5_0.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
31
+ | [Hyperion-3.0-Mistral-7B-alpha-Q4_K_M.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
32
+ | [Hyperion-3.0-Mistral-7B-alpha-Q4_K_S.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
33
+ | [Hyperion-3.0-Mistral-7B-alpha-Q4_0.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
34
+ | [Hyperion-3.0-Mistral-7B-alpha-Q3_K_L.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
35
+ | [Hyperion-3.0-Mistral-7B-alpha-Q3_K_M.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
36
+ | [Hyperion-3.0-Mistral-7B-alpha-Q3_K_S.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
37
+ | [Hyperion-3.0-Mistral-7B-alpha-Q2_K.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF/blob/main/Hyperion-3.0-Mistral-7B-alpha-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
38
+
39
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski