Hugging Face's logo

bartowski
/
dolphincoder-starcoder2-15b-GGUF

Text Generation
GGUF
English
Inference Endpoints
conversational
Model card Files Community
bartowski commited on
Commit
d838827
•
1 Parent(s): df0c447

Llamacpp quants

Browse files
Files changed (15) hide show
  1. .gitattributes +13 -0
  2. README.md +41 -0
  3. dolphincoder-starcoder2-15b-Q2_K.gguf +3 -0
  4. dolphincoder-starcoder2-15b-Q3_K_L.gguf +3 -0
  5. dolphincoder-starcoder2-15b-Q3_K_M.gguf +3 -0
  6. dolphincoder-starcoder2-15b-Q3_K_S.gguf +3 -0
  7. dolphincoder-starcoder2-15b-Q4_0.gguf +3 -0
  8. dolphincoder-starcoder2-15b-Q4_K_M.gguf +3 -0
  9. dolphincoder-starcoder2-15b-Q4_K_S.gguf +3 -0
  10. dolphincoder-starcoder2-15b-Q5_0.gguf +3 -0
  11. dolphincoder-starcoder2-15b-Q5_K_M.gguf +3 -0
  12. dolphincoder-starcoder2-15b-Q5_K_S.gguf +3 -0
  13. dolphincoder-starcoder2-15b-Q6_K.gguf +3 -0
  14. dolphincoder-starcoder2-15b-Q8_0.gguf +3 -0
  15. dolphincoder-starcoder2-15b-fp16.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,16 @@ 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
+ dolphincoder-starcoder2-15b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ dolphincoder-starcoder2-15b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ dolphincoder-starcoder2-15b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ dolphincoder-starcoder2-15b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ dolphincoder-starcoder2-15b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ dolphincoder-starcoder2-15b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ dolphincoder-starcoder2-15b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ dolphincoder-starcoder2-15b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ dolphincoder-starcoder2-15b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ dolphincoder-starcoder2-15b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ dolphincoder-starcoder2-15b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ dolphincoder-starcoder2-15b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ dolphincoder-starcoder2-15b-fp16.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - cognitivecomputations/dolphin
4
+ - jondurbin/airoboros-2.2.1
5
+ - cognitivecomputations/dolphin-coder
6
+ - teknium/openhermes
7
+ - ise-uiuc/Magicoder-OSS-Instruct-75K
8
+ - ise-uiuc/Magicoder-Evol-Instruct-110K
9
+ - m-a-p/Code-Feedback
10
+ - m-a-p/CodeFeedback-Filtered-Instruction
11
+ language:
12
+ - en
13
+ license: bigcode-openrail-m
14
+ quantized_by: bartowski
15
+ pipeline_tag: text-generation
16
+ ---
17
+
18
+ ## Llamacpp Quantizations of dolphincoder-starcoder2-15b
19
+
20
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2354">b2354</a> for quantization.
21
+
22
+ Original model: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b
23
+
24
+ Download a file (not the whole branch) from below:
25
+
26
+ | Filename | Quant type | File Size | Description |
27
+ | -------- | ---------- | --------- | ----------- |
28
+ | [dolphincoder-starcoder2-15b-Q8_0.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q8_0.gguf) | Q8_0 | 16.96GB | Extremely high quality, generally unneeded but max available quant. |
29
+ | [dolphincoder-starcoder2-15b-Q6_K.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q6_K.gguf) | Q6_K | 13.10GB | Very high quality, near perfect, *recommended*. |
30
+ | [dolphincoder-starcoder2-15b-Q5_K_M.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q5_K_M.gguf) | Q5_K_M | 11.43GB | High quality, very usable. |
31
+ | [dolphincoder-starcoder2-15b-Q5_K_S.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q5_K_S.gguf) | Q5_K_S | 11.02GB | High quality, very usable. |
32
+ | [dolphincoder-starcoder2-15b-Q5_0.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q5_0.gguf) | Q5_0 | 11.02GB | High quality, older format, generally not recommended. |
33
+ | [dolphincoder-starcoder2-15b-Q4_K_M.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q4_K_M.gguf) | Q4_K_M | 9.86GB | Good quality, similar to 4.25 bpw. |
34
+ | [dolphincoder-starcoder2-15b-Q4_K_S.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q4_K_S.gguf) | Q4_K_S | 9.25GB | Slightly lower quality with small space savings. |
35
+ | [dolphincoder-starcoder2-15b-Q4_0.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q4_0.gguf) | Q4_0 | 9.06GB | Decent quality, older format, generally not recommended. |
36
+ | [dolphincoder-starcoder2-15b-Q3_K_L.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q3_K_L.gguf) | Q3_K_L | 8.96GB | Lower quality but usable, good for low RAM availability. |
37
+ | [dolphincoder-starcoder2-15b-Q3_K_M.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q3_K_M.gguf) | Q3_K_M | 8.10GB | Even lower quality. |
38
+ | [dolphincoder-starcoder2-15b-Q3_K_S.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q3_K_S.gguf) | Q3_K_S | 6.98GB | Low quality, not recommended. |
39
+ | [dolphincoder-starcoder2-15b-Q2_K.gguf](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-GGUF/blob/main/dolphincoder-starcoder2-15b-Q2_K.gguf) | Q2_K | 6.19GB | Extremely low quality, *not* recommended.
40
+
41
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
dolphincoder-starcoder2-15b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0c3cae9b68d66b24d467583c4cb719b94c35a0ce29aea4e7b707828a4355b6
3
+ size 6192972192
dolphincoder-starcoder2-15b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c53f0e815174c4e92802ea817acb648858a554610e336cc58fb700df7eff56
3
+ size 8965342848
dolphincoder-starcoder2-15b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884329c713e57cab5a87d563012b727eec26f6c5279c8a5da569476d9be51122
3
+ size 8101054080
dolphincoder-starcoder2-15b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2286aafc2448c1c607d091c33bf8164ffac2c85f21d98782d6ed9601c3d6bb7a
3
+ size 6986483328
dolphincoder-starcoder2-15b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0e42955f814920cb21d0f3f7666f11ac1c1609732c2e2f89dc76c4fcbfa2f7
3
+ size 9065417952
dolphincoder-starcoder2-15b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba99d4ceb09f7481015c4bab2262f792fb50c3a776433398e9708e0673221156
3
+ size 9860205792
dolphincoder-starcoder2-15b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8c1580851d8281cadcd53480e2036a93e200803bfc7221ae6870d6974d128e
3
+ size 9255734496
dolphincoder-starcoder2-15b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1997795765a0820a48bf28de763007068c77e72a45bdeca0f5c43ae9a1c1f26f
3
+ size 11022062304
dolphincoder-starcoder2-15b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae7d72b6e053b1269a4f03ee42a6c2da6a50fb9d087ece4ee0dd5ece745bbf8
3
+ size 11431498464
dolphincoder-starcoder2-15b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55fd59cda5b1d322d7ae57a8cd6922095c05cd090d853356bcb3f425f4fc7a22
3
+ size 11022062304
dolphincoder-starcoder2-15b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6188181ffc08bc431eaebae107b4e5426d647aab69c38595002e1714e7a646
3
+ size 13100996928
dolphincoder-starcoder2-15b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca23d5b02c7b055f4cd13ee86da34f188c12fef7631e477c84cb3a18319b332
3
+ size 16965136512
dolphincoder-starcoder2-15b-fp16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7a093df4393f8092bbeb559ed5a921f25993f831939c85b319d00560bcc4a6
3
+ size 31923096128