Compare commits
10 Commits
772626b769
...
0c86a19031
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0c86a19031 | ||
|
|
8573f10169 | ||
|
|
a4f9e0b7d2 | ||
|
|
e1b5827492 | ||
|
|
91e74a1ad0 | ||
|
|
7cede054af | ||
|
|
8f92e840c4 | ||
|
|
eb38f4e43a | ||
|
|
ee0ea6c5fa | ||
|
|
de89ed6e0d |
9
.gitattributes
vendored
9
.gitattributes
vendored
@@ -35,3 +35,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
gpt-oss-nemo-20b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
81
README.md
81
README.md
@@ -1,3 +1,34 @@
|
||||
---
|
||||
base_model: justinj92/gpt-oss-nemo-20b
|
||||
datasets:
|
||||
- HuggingFaceH4/Multilingual-Thinking
|
||||
language:
|
||||
- multilingual
|
||||
- en
|
||||
- es
|
||||
- ar
|
||||
- fr
|
||||
- de
|
||||
- zh
|
||||
- ja
|
||||
- ko
|
||||
- hi
|
||||
- ru
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
mradermacher:
|
||||
readme_rev: 1
|
||||
quantized_by: mradermacher
|
||||
tags:
|
||||
- multilingual
|
||||
- reasoning
|
||||
- thinking
|
||||
- fine-tuned
|
||||
- lora
|
||||
- conversational
|
||||
---
|
||||
## About
|
||||
|
||||
<!-- ### quantize_version: 2 -->
|
||||
<!-- ### output_tensor_quantised: 1 -->
|
||||
<!-- ### convert_type: hf -->
|
||||
@@ -7,3 +38,53 @@
|
||||
<!-- ### quants_skip: -->
|
||||
<!-- ### skip_mmproj: -->
|
||||
static quants of https://huggingface.co/justinj92/gpt-oss-nemo-20b
|
||||
|
||||
<!-- provided-files -->
|
||||
|
||||
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-nemo-20b-GGUF).***
|
||||
|
||||
weighted/imatrix quants are available at https://huggingface.co/mradermacher/gpt-oss-nemo-20b-i1-GGUF
|
||||
## Usage
|
||||
|
||||
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
||||
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
|
||||
more details, including on how to concatenate multi-part files.
|
||||
|
||||
## Provided Quants
|
||||
|
||||
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
||||
|
||||
| Link | Type | Size/GB | Notes |
|
||||
|:-----|:-----|--------:|:------|
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q3_K_S.gguf) | Q3_K_S | 12.2 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q2_K.gguf) | Q2_K | 12.2 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.IQ4_XS.gguf) | IQ4_XS | 12.3 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q3_K_M.gguf) | Q3_K_M | 13.0 | lower quality |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q3_K_L.gguf) | Q3_K_L | 13.4 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q4_K_S.gguf) | Q4_K_S | 14.8 | fast, recommended |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q4_K_M.gguf) | Q4_K_M | 15.9 | fast, recommended |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q5_K_S.gguf) | Q5_K_S | 16.0 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q5_K_M.gguf) | Q5_K_M | 17.0 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q6_K.gguf) | Q6_K | 22.3 | very good quality |
|
||||
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-nemo-20b-GGUF/resolve/main/gpt-oss-nemo-20b.Q8_0.gguf) | Q8_0 | 22.4 | fast, best quality |
|
||||
|
||||
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
||||
types (lower is better):
|
||||
|
||||

|
||||
|
||||
And here are Artefact2's thoughts on the matter:
|
||||
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
||||
|
||||
## FAQ / Model Request
|
||||
|
||||
See https://huggingface.co/mradermacher/model_requests for some answers to
|
||||
questions you might have and/or if you want some other model quantized.
|
||||
|
||||
## Thanks
|
||||
|
||||
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
||||
me use its servers and providing upgrades to my workstation to enable
|
||||
this work in my free time.
|
||||
|
||||
<!-- end -->
|
||||
|
||||
3
gpt-oss-nemo-20b.IQ4_XS.gguf
Normal file
3
gpt-oss-nemo-20b.IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0d8d328184f35062a8e0f4eb0018e318d0e9af93e9697d78ebac12a1143a8cd
|
||||
size 12245779456
|
||||
3
gpt-oss-nemo-20b.Q3_K_L.gguf
Normal file
3
gpt-oss-nemo-20b.Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b83262793b514b47b956ce2f63dfc3fe281054841c2ccc1e5d4de2bd85416257
|
||||
size 13335110656
|
||||
3
gpt-oss-nemo-20b.Q3_K_M.gguf
Normal file
3
gpt-oss-nemo-20b.Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d4cf7e3b52b6288a7b1d6bdcaae8d98b9dbdae22d1200aba94bffbdb336ab9ad
|
||||
size 12916151296
|
||||
3
gpt-oss-nemo-20b.Q3_K_S.gguf
Normal file
3
gpt-oss-nemo-20b.Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:40e49682ceeae9f3265c0393df9ce444a2fda4d6f8eb10d916e6ebb71e6fc246
|
||||
size 12061090816
|
||||
3
gpt-oss-nemo-20b.Q4_K_M.gguf
Normal file
3
gpt-oss-nemo-20b.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b19bdc0989649c02e89811aca235926ca3307a197f1863b901c49322f592c853
|
||||
size 15805136896
|
||||
3
gpt-oss-nemo-20b.Q5_K_M.gguf
Normal file
3
gpt-oss-nemo-20b.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7c60bfcd6182181a2bdd11b2e20a713295a6d7ee27ab3022bbddccf34b63121
|
||||
size 16893062656
|
||||
3
gpt-oss-nemo-20b.Q5_K_S.gguf
Normal file
3
gpt-oss-nemo-20b.Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24281f8eaa0c49948af2b34176fbe134e7e5be33771c10e4695c352117ec15ef
|
||||
size 15892205056
|
||||
3
gpt-oss-nemo-20b.Q6_K.gguf
Normal file
3
gpt-oss-nemo-20b.Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7631484b140c0ba3558643cad3eed03895e53ea5b2e4440b58dabe79906aa942
|
||||
size 22193345536
|
||||
3
gpt-oss-nemo-20b.Q8_0.gguf
Normal file
3
gpt-oss-nemo-20b.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:345b478ee4076ba611cfb81081db63c3ff6d309fe7cf76390b518d6c13962097
|
||||
size 22261912576
|
||||
Reference in New Issue
Block a user