Hugging Face's logo

featherless-ai-quants
/
winglian-Llama-3-8b-64k-PoSE-GGUF

Text Generation
GGUF
Inference Endpoints
Model card Files Community
m8than commited on
Commit
91e628a
·
verified ·
1 Parent(s): 70211e1

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +46 -0
  3. featherless-quants.png +3 -0
  4. winglian-Llama-3-8b-64k-PoSE-IQ4_XS.gguf +3 -0
  5. winglian-Llama-3-8b-64k-PoSE-Q2_K.gguf +3 -0
  6. winglian-Llama-3-8b-64k-PoSE-Q3_K_L.gguf +3 -0
  7. winglian-Llama-3-8b-64k-PoSE-Q3_K_M.gguf +3 -0
  8. winglian-Llama-3-8b-64k-PoSE-Q3_K_S.gguf +3 -0
  9. winglian-Llama-3-8b-64k-PoSE-Q4_K_M.gguf +3 -0
  10. winglian-Llama-3-8b-64k-PoSE-Q4_K_S.gguf +3 -0
  11. winglian-Llama-3-8b-64k-PoSE-Q5_K_M.gguf +3 -0
  12. winglian-Llama-3-8b-64k-PoSE-Q5_K_S.gguf +3 -0
  13. winglian-Llama-3-8b-64k-PoSE-Q6_K.gguf +3 -0
  14. winglian-Llama-3-8b-64k-PoSE-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
+ winglian-Llama-3-8b-64k-PoSE-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
38
+ winglian-Llama-3-8b-64k-PoSE-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ winglian-Llama-3-8b-64k-PoSE-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
40
+ winglian-Llama-3-8b-64k-PoSE-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ winglian-Llama-3-8b-64k-PoSE-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
+ winglian-Llama-3-8b-64k-PoSE-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ winglian-Llama-3-8b-64k-PoSE-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ winglian-Llama-3-8b-64k-PoSE-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ winglian-Llama-3-8b-64k-PoSE-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ winglian-Llama-3-8b-64k-PoSE-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ winglian-Llama-3-8b-64k-PoSE-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: winglian/Llama-3-8b-64k-PoSE
3
+ pipeline_tag: text-generation
4
+ quantized_by: featherless-ai-quants
5
+ ---
6
+
7
+ # winglian/Llama-3-8b-64k-PoSE GGUF Quantizations 🚀
8
+
9
+ ![Featherless AI Quants](./featherless-quants.png)
10
+
11
+ *Optimized GGUF quantization files for enhanced model performance*
12
+
13
+ ---
14
+
15
+ ## Available Quantizations 📊
16
+
17
+ | Quantization Type | File | Size |
18
+ |-------------------|------|------|
19
+ | Q8_0 | [winglian-Llama-3-8b-64k-PoSE-Q8_0.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q8_0.gguf) | 8145.11 MB |
20
+ | Q4_K_S | [winglian-Llama-3-8b-64k-PoSE-Q4_K_S.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q4_K_S.gguf) | 4475.28 MB |
21
+ | Q2_K | [winglian-Llama-3-8b-64k-PoSE-Q2_K.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q2_K.gguf) | 3031.86 MB |
22
+ | Q6_K | [winglian-Llama-3-8b-64k-PoSE-Q6_K.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q6_K.gguf) | 6290.44 MB |
23
+ | Q3_K_M | [winglian-Llama-3-8b-64k-PoSE-Q3_K_M.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q3_K_M.gguf) | 3832.74 MB |
24
+ | Q3_K_S | [winglian-Llama-3-8b-64k-PoSE-Q3_K_S.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q3_K_S.gguf) | 3494.74 MB |
25
+ | Q3_K_L | [winglian-Llama-3-8b-64k-PoSE-Q3_K_L.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q3_K_L.gguf) | 4121.74 MB |
26
+ | Q4_K_M | [winglian-Llama-3-8b-64k-PoSE-Q4_K_M.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q4_K_M.gguf) | 4692.78 MB |
27
+ | Q5_K_S | [winglian-Llama-3-8b-64k-PoSE-Q5_K_S.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q5_K_S.gguf) | 5339.90 MB |
28
+ | Q5_K_M | [winglian-Llama-3-8b-64k-PoSE-Q5_K_M.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-Q5_K_M.gguf) | 5467.40 MB |
29
+ | IQ4_XS | [winglian-Llama-3-8b-64k-PoSE-IQ4_XS.gguf](https://huggingface.co/featherless-ai-quants/winglian-Llama-3-8b-64k-PoSE-GGUF/blob/main/winglian-Llama-3-8b-64k-PoSE-IQ4_XS.gguf) | 4276.62 MB |
30
+
31
+
32
+ ---
33
+
34
+ ## ⚡ Powered by [Featherless AI](https://featherless.ai)
35
+
36
+ ### Key Features
37
+
38
+ - 🔥 **Instant Hosting** - Deploy any Llama model on HuggingFace instantly
39
+ - 🛠️ **Zero Infrastructure** - No server setup or maintenance required
40
+ - 📚 **Vast Compatibility** - Support for 2400+ models and counting
41
+ - 💎 **Affordable Pricing** - Starting at just $10/month
42
+
43
+ ---
44
+
45
+ **Links:**
46
+ [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
winglian-Llama-3-8b-64k-PoSE-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8d39d227ebc7339ef9c543aeefb2f6bd2a3a2ac0c53de5ae6479309f4c400a
3
+ size 4484362560
winglian-Llama-3-8b-64k-PoSE-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5dc33d73ebd6197832c6348a4476e237bec49492a5451f10a06822148100dd
3
+ size 3179131200
winglian-Llama-3-8b-64k-PoSE-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5a0cb7f23afeaa02fc5ab2c8d7e63103a617c699c85614014bbcf9a1b53e08
3
+ size 4321956160
winglian-Llama-3-8b-64k-PoSE-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e296861639b78e7fc4b6e35a028e2c8a4669c361ac42bf19db84035e989a7492
3
+ size 4018917696
winglian-Llama-3-8b-64k-PoSE-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44c315189aec8fb7b71d39dd5a650f5ddb5b48d71333ba1f8f3a36d02116405
3
+ size 3664499008
winglian-Llama-3-8b-64k-PoSE-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325c32771de36d24abfa6642fe3cbf38a2165ccbb6b77fd0e48122a21d625a55
3
+ size 4920734016
winglian-Llama-3-8b-64k-PoSE-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c36152b341357b082a29fee718275a11238999f479148389691b5342fc486992
3
+ size 4692668736
winglian-Llama-3-8b-64k-PoSE-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb94ad21dd78fad48911a94b4dc93757ac25416f48798f952a75419b8868b21
3
+ size 5732987200
winglian-Llama-3-8b-64k-PoSE-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1ca6bad3b25598a9d58b75effe8cbc08b8c59b639b0432f502c3fecb74c336
3
+ size 5599293760
winglian-Llama-3-8b-64k-PoSE-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fe2797ae58462f7a5d9bbb6b062d5506b5d1df8cdb591bc961a29317eb9421
3
+ size 6596006208
winglian-Llama-3-8b-64k-PoSE-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f216fc78f9e961052de61a07a614671a6a37c36b9aa75868d3b4193145a884f
3
+ size 8540770624