prithivMLmods commited on
Commit
15bc9e0
·
verified ·
1 Parent(s): e8128f0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -0
README.md CHANGED
@@ -18,6 +18,33 @@ tags:
18
 
19
  > **GCIRS-Reasoning-1.5B-R1** is a **research-grade reasoning model** fine-tuned from **Qwen2.5-1.5B-Instruct**, focused on **non-fictional reasoning**, **factual consistency**, and **scientific depth**. Trained with reinforcement learning using the **Big Reasoning Traces** dataset from DeepSeek, this model is tailored for complex analytical tasks and scientific rigor in high-stakes or research environments.
20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  ## Quants Usage
22
 
23
  (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
 
18
 
19
  > **GCIRS-Reasoning-1.5B-R1** is a **research-grade reasoning model** fine-tuned from **Qwen2.5-1.5B-Instruct**, focused on **non-fictional reasoning**, **factual consistency**, and **scientific depth**. Trained with reinforcement learning using the **Big Reasoning Traces** dataset from DeepSeek, this model is tailored for complex analytical tasks and scientific rigor in high-stakes or research environments.
20
 
21
+
22
+ ## Model Files
23
+
24
+ | File Name | Format | Size | Precision | Use Case |
25
+ |-----------|--------|------|-----------|----------|
26
+ | `GCIRS-Reasoning-1.5B-R1.F32.gguf` | GGUF | 7.11 GB | F32 | Highest precision, research use |
27
+ | `GCIRS-Reasoning-1.5B-R1.BF16.gguf` | GGUF | 3.56 GB | BF16 | High precision, balanced performance |
28
+ | `GCIRS-Reasoning-1.5B-R1.F16.gguf` | GGUF | 3.56 GB | F16 | High precision, memory efficient |
29
+ | `GCIRS-Reasoning-1.5B-R1.Q8_0.gguf` | GGUF | 1.89 GB | Q8_0 | Excellent quality, moderate compression |
30
+ | `GCIRS-Reasoning-1.5B-R1.Q6_K.gguf` | GGUF | 1.46 GB | Q6_K | Very good quality, good compression |
31
+ | `GCIRS-Reasoning-1.5B-R1.Q5_K_M.gguf` | GGUF | 1.29 GB | Q5_K_M | Balanced quality/size (recommended) |
32
+ | `GCIRS-Reasoning-1.5B-R1.Q5_K_S.gguf` | GGUF | 1.26 GB | Q5_K_S | Good quality, smaller size |
33
+ | `GCIRS-Reasoning-1.5B-R1.Q4_K_M.gguf` | GGUF | 1.12 GB | Q4_K_M | Good balance for most users |
34
+ | `GCIRS-Reasoning-1.5B-R1.Q4_K_S.gguf` | GGUF | 1.07 GB | Q4_K_S | Decent quality, compact size |
35
+ | `GCIRS-Reasoning-1.5B-R1.Q3_K_L.gguf` | GGUF | 980 MB | Q3_K_L | Lower quality, very compact |
36
+ | `GCIRS-Reasoning-1.5B-R1.Q3_K_M.gguf` | GGUF | 924 MB | Q3_K_M | Fast inference, limited quality |
37
+ | `GCIRS-Reasoning-1.5B-R1.Q3_K_S.gguf` | GGUF | 861 MB | Q3_K_S | Fastest inference, basic quality |
38
+ | `GCIRS-Reasoning-1.5B-R1.Q2_K.gguf` | GGUF | 753 MB | Q2_K | Minimal size, experimental use |
39
+
40
+ ### Quick Selection Guide
41
+
42
+ - **For Research/Development**: Use `F32` or `BF16` for maximum accuracy
43
+ - **For Production (Recommended)**: Use `Q5_K_M` or `Q6_K` for best quality/performance balance
44
+ - **For General Use**: Use `Q4_K_M` or `Q4_K_S` for good performance
45
+ - **For Resource-Constrained Environments**: Use `Q3_K_M` or `Q3_K_L`
46
+ - **For Edge Devices**: Use `Q2_K` for minimal footprint
47
+
48
  ## Quants Usage
49
 
50
  (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)