Update README.md
Browse files
README.md
CHANGED
@@ -19,6 +19,112 @@ tags:
|
|
19 |
This model was converted to GGUF format from [`prithivMLmods/Viper-Coder-HybridMini-v1.3`](https://huggingface.co/prithivMLmods/Viper-Coder-HybridMini-v1.3) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
20 |
Refer to the [original model card](https://huggingface.co/prithivMLmods/Viper-Coder-HybridMini-v1.3) for more details on the model.
|
21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
## Use with llama.cpp
|
23 |
Install llama.cpp through brew (works on Mac and Linux)
|
24 |
|
|
|
19 |
This model was converted to GGUF format from [`prithivMLmods/Viper-Coder-HybridMini-v1.3`](https://huggingface.co/prithivMLmods/Viper-Coder-HybridMini-v1.3) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
20 |
Refer to the [original model card](https://huggingface.co/prithivMLmods/Viper-Coder-HybridMini-v1.3) for more details on the model.
|
21 |
|
22 |
+
---
|
23 |
+
Viper-Coder-HybridMini-v1.3
|
24 |
+
-
|
25 |
+
|
26 |
+
|
27 |
+
Viper-Coder-HybridMini-v1.3 is based on the Qwen 2.5 7B modality architecture, designed to be the best
|
28 |
+
for coding and reasoning tasks. It has been fine-tuned on a synthetic
|
29 |
+
dataset leveraging the latest coding logits and CoT datasets, further
|
30 |
+
optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex coding tasks, instruction-following, and text generation.
|
31 |
+
|
32 |
+
|
33 |
+
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
Key Improvements
|
39 |
+
-
|
40 |
+
|
41 |
+
|
42 |
+
Best-in-Class Coding Proficiency: Enhanced understanding of programming languages, debugging, and code generation.
|
43 |
+
Fine-Tuned Instruction Following: Optimized for precise responses, structured outputs (e.g., JSON, YAML), and extended text generation (8K+ tokens).
|
44 |
+
Advanced Logical & Mathematical Reasoning: Improved multi-step problem-solving and theorem proving.
|
45 |
+
Long-Context Mastery: Handles up to 128K tokens with an output capability of 8K tokens per response.
|
46 |
+
Multilingual Code Support: Excels in Python, JavaScript, C++, Java, SQL, and other major programming languages, with documentation in 29+ languages.
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
Quickstart with Transformers
|
55 |
+
-
|
56 |
+
|
57 |
+
|
58 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
59 |
+
|
60 |
+
model_name = "prithivMLmods/Viper-Coder-HybridMini-v1.3"
|
61 |
+
|
62 |
+
model = AutoModelForCausalLM.from_pretrained(
|
63 |
+
model_name,
|
64 |
+
torch_dtype="auto",
|
65 |
+
device_map="auto",
|
66 |
+
trust_remote_code=True
|
67 |
+
)
|
68 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
69 |
+
|
70 |
+
prompt = "Write a Python function to merge two sorted lists."
|
71 |
+
messages = [
|
72 |
+
{"role": "system", "content": "You are an advanced AI assistant with expert-level coding and reasoning abilities."},
|
73 |
+
{"role": "user", "content": prompt}
|
74 |
+
]
|
75 |
+
text = tokenizer.apply_chat_template(
|
76 |
+
messages,
|
77 |
+
tokenize=False,
|
78 |
+
add_generation_prompt=True
|
79 |
+
)
|
80 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
81 |
+
|
82 |
+
generated_ids = model.generate(
|
83 |
+
**model_inputs,
|
84 |
+
max_new_tokens=512
|
85 |
+
)
|
86 |
+
generated_ids = [
|
87 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
88 |
+
]
|
89 |
+
|
90 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
91 |
+
print(response)
|
92 |
+
|
93 |
+
|
94 |
+
|
95 |
+
|
96 |
+
|
97 |
+
|
98 |
+
|
99 |
+
|
100 |
+
Intended Use
|
101 |
+
-
|
102 |
+
|
103 |
+
|
104 |
+
Elite Coding & Debugging: Best-in-class model for writing, analyzing, and optimizing code.
|
105 |
+
Complex Algorithmic Reasoning: Solves intricate logic problems and algorithm-based challenges.
|
106 |
+
Scientific & Mathematical Computation: Advanced support for formulas, equations, and theorem verification.
|
107 |
+
Structured Data Processing: Seamlessly handles JSON, XML, SQL, and data pipeline automation.
|
108 |
+
Multilingual Programming Support: Proficient in Python, JavaScript, C++, Java, Go, and more.
|
109 |
+
Extended Technical Content Generation: Ideal for writing documentation, research papers, and technical blogs.
|
110 |
+
|
111 |
+
|
112 |
+
|
113 |
+
|
114 |
+
|
115 |
+
|
116 |
+
|
117 |
+
Limitations
|
118 |
+
-
|
119 |
+
|
120 |
+
|
121 |
+
Moderate Computational Demand: Requires GPUs/TPUs for smooth inference due to 7B parameters, but more lightweight than larger models.
|
122 |
+
Language-Specific Variability: Performance may vary across different programming languages.
|
123 |
+
Possible Error Propagation: Extended text outputs might introduce logical inconsistencies.
|
124 |
+
Limited Real-World Awareness: The model does not have access to real-time internet updates.
|
125 |
+
Prompt Sensitivity: Performance depends on how well the prompt is structured.
|
126 |
+
|
127 |
+
---
|
128 |
## Use with llama.cpp
|
129 |
Install llama.cpp through brew (works on Mac and Linux)
|
130 |
|