Hugging Face's logo

RichardErkhov
/
onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf

GGUF
Model card Files
xet
Community
RichardErkhov commited on
Commit
dc8f453
·
verified ·
1 Parent(s): 11b7049

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +56 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ starcoder2-3b-instruct-v0.1 - GGUF
11
+ - Model creator: https://huggingface.co/onekq-ai/
12
+ - Original model: https://huggingface.co/onekq-ai/starcoder2-3b-instruct-v0.1/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [starcoder2-3b-instruct-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q2_K.gguf) | Q2_K | 1.14GB |
18
+ | [starcoder2-3b-instruct-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 1.27GB |
19
+ | [starcoder2-3b-instruct-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q3_K.gguf) | Q3_K | 1.46GB |
20
+ | [starcoder2-3b-instruct-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 1.46GB |
21
+ | [starcoder2-3b-instruct-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 1.62GB |
22
+ | [starcoder2-3b-instruct-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 1.56GB |
23
+ | [starcoder2-3b-instruct-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q4_0.gguf) | Q4_0 | 1.63GB |
24
+ | [starcoder2-3b-instruct-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.IQ4_NL.gguf) | IQ4_NL | 1.64GB |
25
+ | [starcoder2-3b-instruct-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 1.64GB |
26
+ | [starcoder2-3b-instruct-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q4_K.gguf) | Q4_K | 1.76GB |
27
+ | [starcoder2-3b-instruct-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 1.76GB |
28
+ | [starcoder2-3b-instruct-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q4_1.gguf) | Q4_1 | 1.8GB |
29
+ | [starcoder2-3b-instruct-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q5_0.gguf) | Q5_0 | 1.96GB |
30
+ | [starcoder2-3b-instruct-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 1.96GB |
31
+ | [starcoder2-3b-instruct-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q5_K.gguf) | Q5_K | 2.03GB |
32
+ | [starcoder2-3b-instruct-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 2.03GB |
33
+ | [starcoder2-3b-instruct-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q5_1.gguf) | Q5_1 | 2.13GB |
34
+ | [starcoder2-3b-instruct-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q6_K.gguf) | Q6_K | 2.32GB |
35
+ | [starcoder2-3b-instruct-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/onekq-ai_-_starcoder2-3b-instruct-v0.1-gguf/blob/main/starcoder2-3b-instruct-v0.1.Q8_0.gguf) | Q8_0 | 3.0GB |
36
+
37
+
38
+
39
+
40
+ Original model description:
41
+ ---
42
+ license: bigcode-openrail-m
43
+ datasets:
44
+ - bigcode/self-oss-instruct-sc2-exec-filter-50k
45
+ base_model:
46
+ - bigcode/starcoder2-3b
47
+ library_name: transformers
48
+ ---
49
+ Starcoder2-3b finetuned the same way as https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 using https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k
50
+
51
+ * Epochs: 1
52
+ * Learning Rate: 0.0001
53
+ * Lora Rank: 8
54
+ * Batch Size: 16
55
+ * Evaluation Split: 0
56
+