初始化项目,由ModelHub XC社区提供模型
Model: mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF Source: Original Platform
This commit is contained in:
46
.gitattributes
vendored
Normal file
46
.gitattributes
vendored
Normal file
@@ -0,0 +1,46 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Nemotron-Cascade-14B-Thinking-impotent-heresy.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7d0d44221a47c9711cc6777c72c5d34273c7d6237ae8a2e3c53764455b1d5b27
|
||||
size 8180363456
|
||||
3
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q2_K.gguf
Normal file
3
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c1939c4f625e0fe93beb90ff3e835e2ddba79111974dcb2159b800ba0316a07a
|
||||
size 5753985216
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:20d411cfdee38aa0fd4d79c499b6eb8257717aab0371ed4e5257a212bf0d2799
|
||||
size 7900652736
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:071ad868207396923211e40b7fd9549c988050d4f177aaebd4b68cc573fcaee7
|
||||
size 7321314496
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bab78d99410dbca768316322d05c60887ed34479e0c968b2fb21ad43421d91ed
|
||||
size 6657107136
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9605731fdae87b6ba763f50251af35d3ce49f494613d0e0d2b97e46ad338ced9
|
||||
size 9001754816
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8643915f3cdd9de12897f6ad605eaee2255520a3219309aa3604cc88384c8801
|
||||
size 8573477056
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc0eeb587c9db17da79cdf58bff5a27c466cb68278d3a239d5fcd9cd9ce9881a
|
||||
size 10514571456
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:388797a49f062f90f76164b06321b1714ff668637908368b26833d49c9f79a2a
|
||||
size 10263896256
|
||||
3
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q6_K.gguf
Normal file
3
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea7ab1cb7e2ca46b870372847c1eba95c50e0c5cf391871f032ed8f71e8e4cc7
|
||||
size 12121939136
|
||||
3
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q8_0.gguf
Normal file
3
Nemotron-Cascade-14B-Thinking-impotent-heresy.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d001111ea4173677f9c5bde4dcb0d997cfbdcd944da9454fce15bc43209e5d22
|
||||
size 15698535616
|
||||
85
README.md
Normal file
85
README.md
Normal file
@@ -0,0 +1,85 @@
|
||||
---
|
||||
base_model: MuXodious/Nemotron-Cascade-14B-Thinking-impotent-heresy
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
license: other
|
||||
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
|
||||
license_name: nvidia-open-model-license
|
||||
mradermacher:
|
||||
readme_rev: 1
|
||||
quantized_by: mradermacher
|
||||
tags:
|
||||
- nvidia
|
||||
- nemotron-cascade
|
||||
- reasoning
|
||||
- general-purpose
|
||||
- SFT
|
||||
- RL
|
||||
- pytorch
|
||||
- heretic
|
||||
- uncensored
|
||||
- decensored
|
||||
- abliterated
|
||||
---
|
||||
## About
|
||||
|
||||
<!-- ### quantize_version: 2 -->
|
||||
<!-- ### output_tensor_quantised: 1 -->
|
||||
<!-- ### convert_type: hf -->
|
||||
<!-- ### vocab_type: -->
|
||||
<!-- ### tags: -->
|
||||
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
|
||||
<!-- ### quants_skip: -->
|
||||
<!-- ### skip_mmproj: -->
|
||||
static quants of https://huggingface.co/MuXodious/Nemotron-Cascade-14B-Thinking-impotent-heresy
|
||||
|
||||
<!-- provided-files -->
|
||||
|
||||
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF).***
|
||||
|
||||
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-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/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q2_K.gguf) | Q2_K | 5.9 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
|
||||
| [GGUF](https://huggingface.co/mradermacher/Nemotron-Cascade-14B-Thinking-impotent-heresy-GGUF/resolve/main/Nemotron-Cascade-14B-Thinking-impotent-heresy.Q8_0.gguf) | Q8_0 | 15.8 | 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 -->
|
||||
Reference in New Issue
Block a user