Downloads · 30 days
178
6% of all-time downloads
saucam_-_Phind-Codefuse-34B-gguf
RichardErkhov/saucam_-_Phind-Codefuse-34B-gguf
saucam_-_Phind-Codefuse-34B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
3K
Public
Repo size
381 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf442 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 15, 2024
- Updated
- Sep 15, 2024
- SHA
- 5df1a1c5
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Phind-Codefuse-34B - GGUF
- Model creator: https://huggingface.co/saucam/
- Original model: https://huggingface.co/saucam/Phind-Codefuse-34B/
| Name | Quant method | Size |
|---|---|---|
| Phind-Codefuse-34B.Q2_K.gguf | Q2_K | 11.65GB |
| Phind-Codefuse-34B.IQ3_XS.gguf | IQ3_XS | 12.93GB |
| Phind-Codefuse-34B.IQ3_S.gguf | IQ3_S | 13.65GB |
| Phind-Codefuse-34B.Q3_K_S.gguf | Q3_K_S | 13.6GB |
| Phind-Codefuse-34B.IQ3_M.gguf | IQ3_M | 14.18GB |
| Phind-Codefuse-34B.Q3_K.gguf | Q3_K | 15.19GB |
| Phind-Codefuse-34B.Q3_K_M.gguf | Q3_K_M | 15.19GB |
| Phind-Codefuse-34B.Q3_K_L.gguf | Q3_K_L | 16.55GB |
| Phind-Codefuse-34B.IQ4_XS.gguf | IQ4_XS | 16.99GB |
| Phind-Codefuse-34B.Q4_0.gguf | Q4_0 | 17.74GB |
| Phind-Codefuse-34B.IQ4_NL.gguf | IQ4_NL | 17.92GB |
| Phind-Codefuse-34B.Q4_K_S.gguf | Q4_K_S | 17.87GB |
| Phind-Codefuse-34B.Q4_K.gguf | Q4_K | 18.83GB |
| Phind-Codefuse-34B.Q4_K_M.gguf | Q4_K_M | 18.83GB |
| Phind-Codefuse-34B.Q4_1.gguf | Q4_1 | 19.69GB |
| Phind-Codefuse-34B.Q5_0.gguf | Q5_0 | 21.64GB |
| Phind-Codefuse-34B.Q5_K_S.gguf | Q5_K_S | 21.64GB |
| Phind-Codefuse-34B.Q5_K.gguf | Q5_K | 22.2GB |
| Phind-Codefuse-34B.Q5_K_M.gguf | Q5_K_M | 22.2GB |
| Phind-Codefuse-34B.Q5_1.gguf | Q5_1 | 23.59GB |
| Phind-Codefuse-34B.Q6_K.gguf | Q6_K | 25.78GB |
| Phind-Codefuse-34B.Q8_0.gguf | Q8_0 | 33.39GB |
Original model description:
tags:
- merge
- mergekit
- lazymergekit
- Phind/Phind-CodeLlama-34B-v2
- codefuse-ai/CodeFuse-CodeLlama-34B base_model:
- Phind/Phind-CodeLlama-34B-v2
- codefuse-ai/CodeFuse-CodeLlama-34B license: mit
Phind-Codefuse-34B
Phind-Codefuse-34B is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- model: Phind/Phind-CodeLlama-34B-v2
parameters:
density: 0.5
weight: 0.6
# No parameters necessary for base model
- model: codefuse-ai/CodeFuse-CodeLlama-34B
parameters:
density: 0.5
weight: 0.4
merge_method: task_arithmetic
base_model: Phind/Phind-CodeLlama-34B-v2
parameters:
int8_mask: true
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "saucam/Phind-Codefuse-34B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
- Created
- Sep 15, 2024
- Updated
- Sep 15, 2024