prithivMLmods commited on
Commit
3d5ce7b
·
verified ·
1 Parent(s): e14af02

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -3
README.md CHANGED
@@ -1,3 +1,44 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - prithivMLmods/FastThink-0.5B-Tiny
7
+ pipeline_tag: text-generation
8
+ library_name: transformers
9
+ tags:
10
+ - text-generation-inference
11
+ ---
12
+ # **FastThink-0.5B-Tiny-GGUF**
13
+
14
+ > FastThink-0.5B-Tiny is a reasoning-focused model based on Qwen2.5. They have released a range of base language models and instruction-tuned language models, spanning from 0.5 billion to 72 billion parameters.
15
+
16
+ ## Model Files
17
+
18
+ | File | Size | Description |
19
+ |------|------|-------------|
20
+ | README.md | 31 Bytes | Project documentation |
21
+ | config.json | 31 Bytes | Model configuration |
22
+ | .gitattributes | 2.39 kB | Git attributes configuration |
23
+ | FastThink-0.5B-Tiny.BF16.gguf | 994 MB | BFloat16 quantized model |
24
+ | FastThink-0.5B-Tiny.F16.gguf | 994 MB | Float16 quantized model |
25
+ | FastThink-0.5B-Tiny.F32.gguf | 1.98 GB | Float32 full precision model |
26
+ | FastThink-0.5B-Tiny.Q2_K.gguf | 339 MB | 2-bit K-quantized model |
27
+ | FastThink-0.5B-Tiny.Q3_K_L.gguf | 369 MB | 3-bit K-quantized model (Large) |
28
+ | FastThink-0.5B-Tiny.Q3_K_M.gguf | 355 MB | 3-bit K-quantized model (Medium) |
29
+ | FastThink-0.5B-Tiny.Q3_K_S.gguf | 338 MB | 3-bit K-quantized model (Small) |
30
+ | FastThink-0.5B-Tiny.Q4_K_M.gguf | 398 MB | 4-bit K-quantized model (Medium) |
31
+ | FastThink-0.5B-Tiny.Q4_K_S.gguf | 385 MB | 4-bit K-quantized model (Small) |
32
+ | FastThink-0.5B-Tiny.Q5_K_M.gguf | 420 MB | 5-bit K-quantized model (Medium) |
33
+ | FastThink-0.5B-Tiny.Q5_K_S.gguf | 413 MB | 5-bit K-quantized model (Small) |
34
+ | FastThink-0.5B-Tiny.Q6_K.gguf | 506 MB | 6-bit K-quantized model |
35
+ | FastThink-0.5B-Tiny.Q8_0.gguf | 531 MB | 8-bit quantized model |
36
+
37
+ ## Quants Usage
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
42
+ types (lower is better):
43
+
44
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)