GGUF
TensorBlock
GGUF
Inference Endpoints
morriszms commited on
Commit
90a0a8a
·
verified ·
1 Parent(s): b298b9a

Upload folder using huggingface_hub

Browse files
.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
+ LosslessMegaCoder-Falcon-40b-mini-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ LosslessMegaCoder-Falcon-40b-mini-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ LosslessMegaCoder-Falcon-40b-mini-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ LosslessMegaCoder-Falcon-40b-mini-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ LosslessMegaCoder-Falcon-40b-mini-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ LosslessMegaCoder-Falcon-40b-mini-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ LosslessMegaCoder-Falcon-40b-mini-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ LosslessMegaCoder-Falcon-40b-mini-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ LosslessMegaCoder-Falcon-40b-mini-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ LosslessMegaCoder-Falcon-40b-mini-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ LosslessMegaCoder-Falcon-40b-mini-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ LosslessMegaCoder-Falcon-40b-mini-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LosslessMegaCoder-Falcon-40b-mini-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25e3b982dc87a0c6e422a7efdcc874cdb32c3e2e4abc468511465f755c7a467
3
+ size 15590318944
LosslessMegaCoder-Falcon-40b-mini-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c303938e1eeb6f74b5b4a6d7561d053bc04a2a82872789d0aa4d31f02e058d
3
+ size 21370594144
LosslessMegaCoder-Falcon-40b-mini-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9194ab50b1cf3c2e372a77ad34b1293c210c9bf8e44bd2bc4f49e5238aa6d205
3
+ size 19866936160
LosslessMegaCoder-Falcon-40b-mini-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40decb99969da135f4fb6117908f2dc85b6a9b1ca24c4382d8b27944d4c87b91
3
+ size 18095104864
LosslessMegaCoder-Falcon-40b-mini-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92d1864b041fdee35621f47ff059e9ae00dffc29807d92774b015fe2f9fcca2
3
+ size 23509689184
LosslessMegaCoder-Falcon-40b-mini-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f61d31d2fd7e1855b19844a68edf12aaa25d3d5bc6bae42b0c4e10da4c3cf18
3
+ size 25189507936
LosslessMegaCoder-Falcon-40b-mini-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042b0959221ab999afe5e127907c9ed741754e3f244e5dfe017d61e98c7a0e2d
3
+ size 23509689184
LosslessMegaCoder-Falcon-40b-mini-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443f23ffd9d4723b20e3d85de9b54d18913fd897c30b4194c42d631a2dc6f154
3
+ size 28605768544
LosslessMegaCoder-Falcon-40b-mini-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71cc4e2034596e3309ac1b8d2d35eb37b1b9a4f955bcfc1a3a5d144e0517883d
3
+ size 30276936544
LosslessMegaCoder-Falcon-40b-mini-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619f446054bbfb895ed8c4e20974847222eb4b7f7148beed9c8293447f096711
3
+ size 28605768544
LosslessMegaCoder-Falcon-40b-mini-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168066e6304939688b76c8427bb09355686c3967a641a2f65fd668731315a47d
3
+ size 34020352864
LosslessMegaCoder-Falcon-40b-mini-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07b2f275400fdf3f12b1ab4c70a455a5972638f83d3900f5acf2f167d7b8c78
3
+ size 43894006624
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
5
+ tags:
6
+ - TensorBlock
7
+ - GGUF
8
+ base_model: rombodawg/LosslessMegaCoder-Falcon-40b-mini
9
+ ---
10
+
11
+ <div style="width: auto; margin-left: auto; margin-right: auto">
12
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
+ </div>
14
+ <div style="display: flex; justify-content: space-between; width: 100%;">
15
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
16
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
17
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
18
+ </p>
19
+ </div>
20
+ </div>
21
+
22
+ ## rombodawg/LosslessMegaCoder-Falcon-40b-mini - GGUF
23
+
24
+ This repo contains GGUF format model files for [rombodawg/LosslessMegaCoder-Falcon-40b-mini](https://huggingface.co/rombodawg/LosslessMegaCoder-Falcon-40b-mini).
25
+
26
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
27
+
28
+ <div style="text-align: left; margin: 20px 0;">
29
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
30
+ Run them on the TensorBlock client using your local machine ↗
31
+ </a>
32
+ </div>
33
+
34
+ ## Prompt template
35
+
36
+ ```
37
+
38
+ ```
39
+
40
+ ## Model file specification
41
+
42
+ | Filename | Quant type | File Size | Description |
43
+ | -------- | ---------- | --------- | ----------- |
44
+ | [LosslessMegaCoder-Falcon-40b-mini-Q2_K.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q2_K.gguf) | Q2_K | 14.520 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [LosslessMegaCoder-Falcon-40b-mini-Q3_K_S.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q3_K_S.gguf) | Q3_K_S | 16.852 GB | very small, high quality loss |
46
+ | [LosslessMegaCoder-Falcon-40b-mini-Q3_K_M.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q3_K_M.gguf) | Q3_K_M | 18.503 GB | very small, high quality loss |
47
+ | [LosslessMegaCoder-Falcon-40b-mini-Q3_K_L.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q3_K_L.gguf) | Q3_K_L | 19.903 GB | small, substantial quality loss |
48
+ | [LosslessMegaCoder-Falcon-40b-mini-Q4_0.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q4_0.gguf) | Q4_0 | 21.895 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [LosslessMegaCoder-Falcon-40b-mini-Q4_K_S.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q4_K_S.gguf) | Q4_K_S | 21.895 GB | small, greater quality loss |
50
+ | [LosslessMegaCoder-Falcon-40b-mini-Q4_K_M.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q4_K_M.gguf) | Q4_K_M | 23.460 GB | medium, balanced quality - recommended |
51
+ | [LosslessMegaCoder-Falcon-40b-mini-Q5_0.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q5_0.gguf) | Q5_0 | 26.641 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [LosslessMegaCoder-Falcon-40b-mini-Q5_K_S.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q5_K_S.gguf) | Q5_K_S | 26.641 GB | large, low quality loss - recommended |
53
+ | [LosslessMegaCoder-Falcon-40b-mini-Q5_K_M.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q5_K_M.gguf) | Q5_K_M | 28.198 GB | large, very low quality loss - recommended |
54
+ | [LosslessMegaCoder-Falcon-40b-mini-Q6_K.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q6_K.gguf) | Q6_K | 31.684 GB | very large, extremely low quality loss |
55
+ | [LosslessMegaCoder-Falcon-40b-mini-Q8_0.gguf](https://huggingface.co/tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF/blob/main/LosslessMegaCoder-Falcon-40b-mini-Q8_0.gguf) | Q8_0 | 40.879 GB | very large, extremely low quality loss - not recommended |
56
+
57
+
58
+ ## Downloading instruction
59
+
60
+ ### Command line
61
+
62
+ Firstly, install Huggingface Client
63
+
64
+ ```shell
65
+ pip install -U "huggingface_hub[cli]"
66
+ ```
67
+
68
+ Then, downoad the individual model file the a local directory
69
+
70
+ ```shell
71
+ huggingface-cli download tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF --include "LosslessMegaCoder-Falcon-40b-mini-Q2_K.gguf" --local-dir MY_LOCAL_DIR
72
+ ```
73
+
74
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/LosslessMegaCoder-Falcon-40b-mini-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
78
+ ```