Hugging Face's logo

RichardErkhov
/
Bin12345_-_AutoCoder_S_6.7B-gguf

GGUF
conversational
Model card Files
xet
Community
RichardErkhov commited on
Commit
fa4843d
·
verified ·
1 Parent(s): 1bc9b6b

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ AutoCoder_S_6.7B - GGUF
11
+ - Model creator: https://huggingface.co/Bin12345/
12
+ - Original model: https://huggingface.co/Bin12345/AutoCoder_S_6.7B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [AutoCoder_S_6.7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q2_K.gguf) | Q2_K | 2.36GB |
18
+ | [AutoCoder_S_6.7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ3_XS.gguf) | IQ3_XS | 2.61GB |
19
+ | [AutoCoder_S_6.7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ3_S.gguf) | IQ3_S | 2.75GB |
20
+ | [AutoCoder_S_6.7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
21
+ | [AutoCoder_S_6.7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ3_M.gguf) | IQ3_M | 2.9GB |
22
+ | [AutoCoder_S_6.7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K.gguf) | Q3_K | 3.07GB |
23
+ | [AutoCoder_S_6.7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
24
+ | [AutoCoder_S_6.7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
25
+ | [AutoCoder_S_6.7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
26
+ | [AutoCoder_S_6.7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_0.gguf) | Q4_0 | 3.56GB |
27
+ | [AutoCoder_S_6.7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.IQ4_NL.gguf) | IQ4_NL | 3.59GB |
28
+ | [AutoCoder_S_6.7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
29
+ | [AutoCoder_S_6.7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_K.gguf) | Q4_K | 3.8GB |
30
+ | [AutoCoder_S_6.7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
31
+ | [AutoCoder_S_6.7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q4_1.gguf) | Q4_1 | 3.95GB |
32
+ | [AutoCoder_S_6.7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_0.gguf) | Q5_0 | 4.33GB |
33
+ | [AutoCoder_S_6.7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
34
+ | [AutoCoder_S_6.7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_K.gguf) | Q5_K | 4.46GB |
35
+ | [AutoCoder_S_6.7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_K_M.gguf) | Q5_K_M | 4.46GB |
36
+ | [AutoCoder_S_6.7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q5_1.gguf) | Q5_1 | 4.72GB |
37
+ | [AutoCoder_S_6.7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q6_K.gguf) | Q6_K | 5.15GB |
38
+ | [AutoCoder_S_6.7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Bin12345_-_AutoCoder_S_6.7B-gguf/blob/main/AutoCoder_S_6.7B.Q8_0.gguf) | Q8_0 | 6.67GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ ---
47
+
48
+ We introduced a new model designed for the Code generation task. It 33B version's test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024). (90.9% vs 90.2%).
49
+
50
+ Additionally, compared to previous open-source models, AutoCoder offers a new feature: it can **automatically install the required packages** and attempt to run the code until it deems there are no issues, **whenever the user wishes to execute the code**.
51
+
52
+ This is the 6.7B version of AutoCoder. Its base model is deepseeker-coder.
53
+
54
+ See details on the [AutoCoder GitHub](https://github.com/bin123apple/AutoCoder).
55
+
56
+ Simple test script:
57
+
58
+ ```
59
+ model_path = ""
60
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
61
+ model = AutoModelForCausalLM.from_pretrained(model_path,
62
+ device_map="auto")
63
+
64
+ HumanEval = load_dataset("evalplus/humanevalplus")
65
+
66
+ Input = "" # input your question here
67
+
68
+ messages=[
69
+ { 'role': 'user', 'content': Input}
70
+ ]
71
+ inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True,
72
+ return_tensors="pt").to(model.device)
73
+
74
+ outputs = model.generate(inputs,
75
+ max_new_tokens=1024,
76
+ do_sample=False,
77
+ temperature=0.0,
78
+ top_p=1.0,
79
+ num_return_sequences=1,
80
+ eos_token_id=tokenizer.eos_token_id)
81
+
82
+ answer = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
83
+ ```
84
+
85
+ Paper: https://arxiv.org/abs/2405.14906
86
+