Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +90 -0
- Reasoning-SmolLM2-135M-Q2_K.gguf +3 -0
- Reasoning-SmolLM2-135M-Q3_K_L.gguf +3 -0
- Reasoning-SmolLM2-135M-Q3_K_M.gguf +3 -0
- Reasoning-SmolLM2-135M-Q3_K_S.gguf +3 -0
- Reasoning-SmolLM2-135M-Q4_0.gguf +3 -0
- Reasoning-SmolLM2-135M-Q4_K_M.gguf +3 -0
- Reasoning-SmolLM2-135M-Q4_K_S.gguf +3 -0
- Reasoning-SmolLM2-135M-Q5_0.gguf +3 -0
- Reasoning-SmolLM2-135M-Q5_K_M.gguf +3 -0
- Reasoning-SmolLM2-135M-Q5_K_S.gguf +3 -0
- Reasoning-SmolLM2-135M-Q6_K.gguf +3 -0
- Reasoning-SmolLM2-135M-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 |
+
Reasoning-SmolLM2-135M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Reasoning-SmolLM2-135M-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Reasoning-SmolLM2-135M-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Reasoning-SmolLM2-135M-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Reasoning-SmolLM2-135M-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Reasoning-SmolLM2-135M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Reasoning-SmolLM2-135M-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Reasoning-SmolLM2-135M-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Reasoning-SmolLM2-135M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Reasoning-SmolLM2-135M-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Reasoning-SmolLM2-135M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Reasoning-SmolLM2-135M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
base_model: prithivMLmods/Reasoning-SmolLM2-135M
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
library_name: transformers
|
8 |
+
tags:
|
9 |
+
- trl
|
10 |
+
- smolLM
|
11 |
+
- llama
|
12 |
+
- CoT
|
13 |
+
- Thinker
|
14 |
+
- LlamaForCausalLM
|
15 |
+
- TensorBlock
|
16 |
+
- GGUF
|
17 |
+
---
|
18 |
+
|
19 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
20 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
21 |
+
</div>
|
22 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
23 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
24 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
25 |
+
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>
|
26 |
+
</p>
|
27 |
+
</div>
|
28 |
+
</div>
|
29 |
+
|
30 |
+
## prithivMLmods/Reasoning-SmolLM2-135M - GGUF
|
31 |
+
|
32 |
+
This repo contains GGUF format model files for [prithivMLmods/Reasoning-SmolLM2-135M](https://huggingface.co/prithivMLmods/Reasoning-SmolLM2-135M).
|
33 |
+
|
34 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
|
35 |
+
|
36 |
+
<div style="text-align: left; margin: 20px 0;">
|
37 |
+
<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;">
|
38 |
+
Run them on the TensorBlock client using your local machine ↗
|
39 |
+
</a>
|
40 |
+
</div>
|
41 |
+
|
42 |
+
## Prompt template
|
43 |
+
|
44 |
+
```
|
45 |
+
<|im_start|>system
|
46 |
+
{system_prompt}<|im_end|>
|
47 |
+
<|im_start|>user
|
48 |
+
{prompt}<|im_end|>
|
49 |
+
<|im_start|>assistant
|
50 |
+
```
|
51 |
+
|
52 |
+
## Model file specification
|
53 |
+
|
54 |
+
| Filename | Quant type | File Size | Description |
|
55 |
+
| -------- | ---------- | --------- | ----------- |
|
56 |
+
| [Reasoning-SmolLM2-135M-Q2_K.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q2_K.gguf) | Q2_K | 0.088 GB | smallest, significant quality loss - not recommended for most purposes |
|
57 |
+
| [Reasoning-SmolLM2-135M-Q3_K_S.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q3_K_S.gguf) | Q3_K_S | 0.088 GB | very small, high quality loss |
|
58 |
+
| [Reasoning-SmolLM2-135M-Q3_K_M.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q3_K_M.gguf) | Q3_K_M | 0.094 GB | very small, high quality loss |
|
59 |
+
| [Reasoning-SmolLM2-135M-Q3_K_L.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q3_K_L.gguf) | Q3_K_L | 0.098 GB | small, substantial quality loss |
|
60 |
+
| [Reasoning-SmolLM2-135M-Q4_0.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q4_0.gguf) | Q4_0 | 0.092 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
61 |
+
| [Reasoning-SmolLM2-135M-Q4_K_S.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q4_K_S.gguf) | Q4_K_S | 0.102 GB | small, greater quality loss |
|
62 |
+
| [Reasoning-SmolLM2-135M-Q4_K_M.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q4_K_M.gguf) | Q4_K_M | 0.105 GB | medium, balanced quality - recommended |
|
63 |
+
| [Reasoning-SmolLM2-135M-Q5_0.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q5_0.gguf) | Q5_0 | 0.105 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
64 |
+
| [Reasoning-SmolLM2-135M-Q5_K_S.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q5_K_S.gguf) | Q5_K_S | 0.110 GB | large, low quality loss - recommended |
|
65 |
+
| [Reasoning-SmolLM2-135M-Q5_K_M.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q5_K_M.gguf) | Q5_K_M | 0.112 GB | large, very low quality loss - recommended |
|
66 |
+
| [Reasoning-SmolLM2-135M-Q6_K.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q6_K.gguf) | Q6_K | 0.138 GB | very large, extremely low quality loss |
|
67 |
+
| [Reasoning-SmolLM2-135M-Q8_0.gguf](https://huggingface.co/tensorblock/Reasoning-SmolLM2-135M-GGUF/blob/main/Reasoning-SmolLM2-135M-Q8_0.gguf) | Q8_0 | 0.145 GB | very large, extremely low quality loss - not recommended |
|
68 |
+
|
69 |
+
|
70 |
+
## Downloading instruction
|
71 |
+
|
72 |
+
### Command line
|
73 |
+
|
74 |
+
Firstly, install Huggingface Client
|
75 |
+
|
76 |
+
```shell
|
77 |
+
pip install -U "huggingface_hub[cli]"
|
78 |
+
```
|
79 |
+
|
80 |
+
Then, downoad the individual model file the a local directory
|
81 |
+
|
82 |
+
```shell
|
83 |
+
huggingface-cli download tensorblock/Reasoning-SmolLM2-135M-GGUF --include "Reasoning-SmolLM2-135M-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
84 |
+
```
|
85 |
+
|
86 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
87 |
+
|
88 |
+
```shell
|
89 |
+
huggingface-cli download tensorblock/Reasoning-SmolLM2-135M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
90 |
+
```
|
Reasoning-SmolLM2-135M-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d014ff191909bb84301c93be45d757cb5a4269fa6aa26c0c565dac219bead48
|
3 |
+
size 88202112
|
Reasoning-SmolLM2-135M-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:680052d21e29438daf8bedf41e350319bb32cf802d019676b438f5d4ff6d8eb9
|
3 |
+
size 97533312
|
Reasoning-SmolLM2-135M-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:041fc3e691b7130718496a34bc3638dd5e938babef1ec40c3b221a120d9b348d
|
3 |
+
size 93510528
|
Reasoning-SmolLM2-135M-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ed387a98f6691f7f2b6a44ba5e85ba595007a18c3eefab2b8069210b2837f26
|
3 |
+
size 88202112
|
Reasoning-SmolLM2-135M-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb8da497bf992d8c75ff70086b1aacfbb4a5d4929f988e29e6aeee326b96fd52
|
3 |
+
size 91727232
|
Reasoning-SmolLM2-135M-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1091aa243b6df84734bb75984cc506b896c8d51158dcab6fc48d6e02a28b7b2c
|
3 |
+
size 105454464
|
Reasoning-SmolLM2-135M-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7061b33e90006e2b62b08f681beef4ffd3a465e289a3ff137a14a721bdef3fd
|
3 |
+
size 102039936
|
Reasoning-SmolLM2-135M-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a1c41914a9a2e70f364d0ed01019cc6be4b75e32750270682f8de9fd5bfd4df
|
3 |
+
size 104998272
|
Reasoning-SmolLM2-135M-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37bf528147d384ea7c10b9004e637e4470c51d80be2a9fae5d07549f4a371587
|
3 |
+
size 112103808
|
Reasoning-SmolLM2-135M-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65f75a79740df043e7cc2e1efd60b1bea5f7a5428f00486156f66304f3008b73
|
3 |
+
size 109974912
|
Reasoning-SmolLM2-135M-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fac7aa77bffc3c9599a17e4229d694cfbf02a44b2150d9b02acad8630005d825
|
3 |
+
size 138383232
|
Reasoning-SmolLM2-135M-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a41ca8b1d7fc2debf84a1d82e4980f13743ad0d492bcd8e866dd886a6dbf9f5
|
3 |
+
size 144811392
|