bartowski commited on
Commit
fba6140
1 Parent(s): b5f6d9f

Llamacpp quants

Browse files
.gitattributes CHANGED
@@ -33,3 +33,19 @@ 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
+ Mistral-7B-v0.1-ORPO-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Mistral-7B-v0.1-ORPO-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Mistral-7B-v0.1-ORPO-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Mistral-7B-v0.1-ORPO-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Mistral-7B-v0.1-ORPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Mistral-7B-v0.1-ORPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Mistral-7B-v0.1-ORPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Mistral-7B-v0.1-ORPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Mistral-7B-v0.1-ORPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Mistral-7B-v0.1-ORPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Mistral-7B-v0.1-ORPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Mistral-7B-v0.1-ORPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Mistral-7B-v0.1-ORPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Mistral-7B-v0.1-ORPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Mistral-7B-v0.1-ORPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Mistral-7B-v0.1-ORPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Mistral-7B-v0.1-ORPO-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb0822425d5b500b5b7f2759a11fcd8fc60d09b9d7b188413b7ff4ca6a9526f
3
+ size 3284901952
Mistral-7B-v0.1-ORPO-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c559ab42078e237af750485598476c9441c364938f50ddaf017eb089f5ba08f2
3
+ size 3182403648
Mistral-7B-v0.1-ORPO-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d14ccf49f20d5f063cf2320be641006e52da0afe75d70cd8c6fdec79b5900db
3
+ size 4155065472
Mistral-7B-v0.1-ORPO-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40afe7afb503c886382b553f17643c65bedfbcc27a0f838c10800f530ccd8ea3
3
+ size 3944399744
Mistral-7B-v0.1-ORPO-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f6afc9db14a307c9fd97c2e383e1711a891aba7eee2956f720459ded9539a2
3
+ size 2719251712
Mistral-7B-v0.1-ORPO-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfabb71c94d294e0800a32cc913aefd96ccbc212664201fe0413ae6301c26e3
3
+ size 3822035008
Mistral-7B-v0.1-ORPO-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade6d108fae6af13892102bd94293bf94f462cd29fe23977b28f775e3081a24f
3
+ size 3518996544
Mistral-7B-v0.1-ORPO-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56a614fbc9e3ea50196fa8a997e96d8728168fd9d941a91b3cd2ce7f9e06bc7
3
+ size 3164577856
Mistral-7B-v0.1-ORPO-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a1e0fc93c00d3b61e11c97d663dc714f3cd2d18c5ecda99bdb038aeeab7346
3
+ size 4108928128
Mistral-7B-v0.1-ORPO-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a99fa1dfd93fdf98a86b88796175a16d2444fd0eb0e2685544c3c22a847145c
3
+ size 4368450688
Mistral-7B-v0.1-ORPO-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc454389dd68f03d3593a550f3830d8a3fc513c3541e0f4de3d6c864081943a
3
+ size 4140385408
Mistral-7B-v0.1-ORPO-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64c55373e1b9d7eedea84eeab023e1ae089eb1667e8cc937b154e20a1cea6cb
3
+ size 4997728384
Mistral-7B-v0.1-ORPO-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2f2be9a786e78e7f4bca966a1982668a2b7f9b1f95c8dd24bb3357f29d5ef6
3
+ size 5131421824
Mistral-7B-v0.1-ORPO-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b1763a55736f2123d0b9baffae1f9881c8df18d8716d88bd23ef675ce89f70
3
+ size 4997728384
Mistral-7B-v0.1-ORPO-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e22edc296aab22434e3a91ef3ca98cdbefdb5bcea8df2516c9e5f9034960592
3
+ size 5942078656
Mistral-7B-v0.1-ORPO-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c8605b0a69738912e4a394b24752e07fd3067f4ecad29015e4da6863a0f4ed
3
+ size 7695875136
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ tags:
7
+ - orpo
8
+ - qlora
9
+ - trl
10
+ datasets:
11
+ - alvarobartt/dpo-mix-7k-simplified
12
+ - argilla/dpo-mix-7k
13
+ base_model: mistralai/Mistral-7B-v0.1
14
+ pipeline_tag: text-generation
15
+ inference: false
16
+ quantized_by: bartowski
17
+ ---
18
+
19
+ ## Llamacpp Quantizations of Mistral-7B-v0.1-ORPO
20
+
21
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
22
+
23
+ Original model: https://huggingface.co/alvarobartt/Mistral-7B-v0.1-ORPO
24
+
25
+ Download a file (not the whole branch) from below:
26
+
27
+ | Filename | Quant type | File Size | Description |
28
+ | -------- | ---------- | --------- | ----------- |
29
+ | [Mistral-7B-v0.1-ORPO-Q8_0.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
30
+ | [Mistral-7B-v0.1-ORPO-Q6_K.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
31
+ | [Mistral-7B-v0.1-ORPO-Q5_K_M.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
32
+ | [Mistral-7B-v0.1-ORPO-Q5_K_S.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
33
+ | [Mistral-7B-v0.1-ORPO-Q5_0.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
34
+ | [Mistral-7B-v0.1-ORPO-Q4_K_M.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
35
+ | [Mistral-7B-v0.1-ORPO-Q4_K_S.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
36
+ | [Mistral-7B-v0.1-ORPO-IQ4_NL.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-IQ4_NL.gguf) | IQ4_NL | 4.15GB | Good quality, similar to Q4_K_S, new method of quanting, |
37
+ | [Mistral-7B-v0.1-ORPO-IQ4_XS.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-IQ4_XS.gguf) | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. |
38
+ | [Mistral-7B-v0.1-ORPO-Q4_0.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
39
+ | [Mistral-7B-v0.1-ORPO-IQ3_M.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. |
40
+ | [Mistral-7B-v0.1-ORPO-IQ3_S.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
41
+ | [Mistral-7B-v0.1-ORPO-Q3_K_L.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
42
+ | [Mistral-7B-v0.1-ORPO-Q3_K_M.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
43
+ | [Mistral-7B-v0.1-ORPO-Q3_K_S.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
44
+ | [Mistral-7B-v0.1-ORPO-Q2_K.gguf](https://huggingface.co/bartowski/Mistral-7B-v0.1-ORPO-GGUF/blob/main/Mistral-7B-v0.1-ORPO-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
45
+
46
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski