HF中国镜像站's logo

featherless-ai-quants
/
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF

Text Generation
GGUF
Inference Endpoints
Model card Files Community
m8than commited on
Commit
ac8f53b
·
verified ·
1 Parent(s): 2d2eb06

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +47 -0
  3. featherless-quants.png +3 -0
  4. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-IQ4_XS.gguf +3 -0
  5. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q2_K.gguf +3 -0
  6. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_L.gguf +3 -0
  7. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_M.gguf +3 -0
  8. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_S.gguf +3 -0
  9. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_M.gguf +3 -0
  10. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_S.gguf +3 -0
  11. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_M.gguf +3 -0
  12. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_S.gguf +3 -0
  13. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q6_K.gguf +3 -0
  14. neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q8_0.gguf +3 -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
+ featherless-quants.png filter=lfs diff=lfs merge=lfs -text
37
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
38
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
40
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: neuralmagic/SparseLlama-3-8B-pruned_50.2of4
3
+ pipeline_tag: text-generation
4
+ quantized_by: featherless-ai-quants
5
+ ---
6
+
7
+ # neuralmagic/SparseLlama-3-8B-pruned_50.2of4 GGUF Quantizations 🚀
8
+
9
+ ![Featherless AI Quants](./featherless-quants.png)
10
+
11
+ *Optimized GGUF quantization files for enhanced model performance*
12
+
13
+ > Powered by [Featherless AI](https://featherless.ai) - run any model you'd like for a simple small fee.
14
+ ---
15
+
16
+ ## Available Quantizations 📊
17
+
18
+ | Quantization Type | File | Size |
19
+ |-------------------|------|------|
20
+ | IQ4_XS | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-IQ4_XS.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-IQ4_XS.gguf) | 4276.62 MB |
21
+ | Q2_K | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q2_K.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q2_K.gguf) | 3031.86 MB |
22
+ | Q3_K_L | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_L.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_L.gguf) | 4121.74 MB |
23
+ | Q3_K_M | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_M.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_M.gguf) | 3832.74 MB |
24
+ | Q3_K_S | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_S.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_S.gguf) | 3494.74 MB |
25
+ | Q4_K_M | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_M.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_M.gguf) | 4692.78 MB |
26
+ | Q4_K_S | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_S.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_S.gguf) | 4475.28 MB |
27
+ | Q5_K_M | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_M.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_M.gguf) | 5467.40 MB |
28
+ | Q5_K_S | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_S.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_S.gguf) | 5339.90 MB |
29
+ | Q6_K | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q6_K.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q6_K.gguf) | 6290.44 MB |
30
+ | Q8_0 | [neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q8_0.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUF/blob/main/neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q8_0.gguf) | 8145.11 MB |
31
+
32
+
33
+ ---
34
+
35
+ ## ⚡ Powered by [Featherless AI](https://featherless.ai)
36
+
37
+ ### Key Features
38
+
39
+ - 🔥 **Instant Hosting** - Deploy any Llama model on HuggingFace instantly
40
+ - 🛠️ **Zero Infrastructure** - No server setup or maintenance required
41
+ - 📚 **Vast Compatibility** - Support for 2400+ models and counting
42
+ - 💎 **Affordable Pricing** - Starting at just $10/month
43
+
44
+ ---
45
+
46
+ **Links:**
47
+ [Get Started](https://featherless.ai) | [Documentation](https://featherless.ai/docs) | [Models](https://featherless.ai/models)
featherless-quants.png ADDED

Git LFS Details

  • SHA256: 2e1b4d66c8306c7b0614089381fdf86ea4efb02dffb78d22767a084cb8b88d6b
  • Pointer size: 132 Bytes
  • Size of remote file: 1.61 MB
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc83bc1dde1a63dc159ebf988bae50d123eec5c6ecd11bb4c35c02f02dae8d0
3
+ size 4484362624
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba54d2a1be31b3021b2bb207fa5da0642eafda9aeeb3389114cc016f7605717
3
+ size 3179131264
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bb94fe40ab187dd667b5a485283e4517d8240f3bce2492b58865fd604e6ed5
3
+ size 4321956224
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7461585304c8ecaadce36bb3b96c5167d0559d719e9cc641e2106da2b36fb27e
3
+ size 4018917760
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd2fda40f9e5c9b26c7efe517acdf624046aaf90aa2105e4e02c48fc5d932b1
3
+ size 3664499072
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4b76e184e0c8c21c389d76cf911d89f3d58ec34261d363eafe07c0a99d2cba
3
+ size 4920734080
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c942b7aaef67b392a4076dde7b414742d10cd384cfcb62a259159419b00b84d
3
+ size 4692668800
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f0c46c59922ba39bb5b65eb2394ee5daf222a93184970bbb455698914f3cd9
3
+ size 5732987264
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b4f7db7e3966d7c440b0954d0090cd193fbc9dcff9deef59a865bea387ef0d
3
+ size 5599293824
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae51776daa124a97ba549e998a73518222f2b006635987414b7fc17fa66e14f
3
+ size 6596006272
neuralmagic-SparseLlama-3-8B-pruned_50.2of4-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e9627577310773ad6e005704f7335d886b69c123db759ae59a11de134bf26e
3
+ size 8540770688