初始化项目，由ModelHub XC社区提供模型
Model: afrideva/open_llama_3b_code_instruct_0.1-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
42
.gitattributes
vendored
Normal file
42
.gitattributes
vendored
Normal file
@@ -0,0 +1,42 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.fp16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.q2_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
open_llama_3b_code_instruct_0.1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
153
README.md
Normal file
153
README.md
Normal file
@@ -0,0 +1,153 @@
|
||||
---
|
||||
base_model: mwitiderrick/open_llama_3b_code_instruct_0.1
|
||||
created_by: mwitiderrick
|
||||
datasets:
|
||||
- mwitiderrick/AlpacaCode
|
||||
inference: false
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
model-index:
|
||||
- name: mwitiderrick/open_llama_3b_instruct_v_0.2
|
||||
results:
|
||||
- dataset:
|
||||
name: hellaswag
|
||||
type: hellaswag
|
||||
metrics:
|
||||
- name: hellaswag(0-Shot)
|
||||
type: hellaswag (0-Shot)
|
||||
value: 0.6581
|
||||
task:
|
||||
type: text-generation
|
||||
- dataset:
|
||||
name: winogrande
|
||||
type: winogrande
|
||||
metrics:
|
||||
- name: winogrande(0-Shot)
|
||||
type: winogrande (0-Shot)
|
||||
value: 0.6267
|
||||
task:
|
||||
type: text-generation
|
||||
- dataset:
|
||||
name: arc_challenge
|
||||
type: arc_challenge
|
||||
metrics:
|
||||
- name: arc_challenge(0-Shot)
|
||||
type: arc_challenge (0-Shot)
|
||||
value: 0.3712
|
||||
source:
|
||||
name: open_llama_3b_instruct_v_0.2 model card
|
||||
url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
|
||||
task:
|
||||
type: text-generation
|
||||
model_creator: mwitiderrick
|
||||
model_name: open_llama_3b_code_instruct_0.1
|
||||
model_type: llama
|
||||
pipeline_tag: text-generation
|
||||
prompt_template: '### Instruction:\n
|
||||
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
|
||||
'
|
||||
quantized_by: afrideva
|
||||
tags:
|
||||
- transformers
|
||||
- gguf
|
||||
- ggml
|
||||
- quantized
|
||||
- q2_k
|
||||
- q3_k_m
|
||||
- q4_k_m
|
||||
- q5_k_m
|
||||
- q6_k
|
||||
- q8_0
|
||||
---
|
||||
# mwitiderrick/open_llama_3b_code_instruct_0.1-GGUF
|
||||
|
||||
Quantized GGUF model files for [open_llama_3b_code_instruct_0.1](https://huggingface.co/mwitiderrick/open_llama_3b_code_instruct_0.1) from [mwitiderrick](https://huggingface.co/mwitiderrick)
|
||||
|
||||
|
||||
| Name | Quant method | Size |
|
||||
| ---- | ---- | ---- |
|
||||
| [open_llama_3b_code_instruct_0.1.fp16.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.fp16.gguf) | fp16 | 6.86 GB |
|
||||
| [open_llama_3b_code_instruct_0.1.q2_k.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.q2_k.gguf) | q2_k | 2.15 GB |
|
||||
| [open_llama_3b_code_instruct_0.1.q3_k_m.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.q3_k_m.gguf) | q3_k_m | 2.27 GB |
|
||||
| [open_llama_3b_code_instruct_0.1.q4_k_m.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.q4_k_m.gguf) | q4_k_m | 2.58 GB |
|
||||
| [open_llama_3b_code_instruct_0.1.q5_k_m.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.q5_k_m.gguf) | q5_k_m | 2.76 GB |
|
||||
| [open_llama_3b_code_instruct_0.1.q6_k.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.q6_k.gguf) | q6_k | 3.64 GB |
|
||||
| [open_llama_3b_code_instruct_0.1.q8_0.gguf](https://huggingface.co/afrideva/open_llama_3b_code_instruct_0.1-GGUF/resolve/main/open_llama_3b_code_instruct_0.1.q8_0.gguf) | q8_0 | 3.64 GB |
|
||||
|
||||
|
||||
|
||||
## Original Model Card:
|
||||
# OpenLLaMA Code Instruct: An Open Reproduction of LLaMA
|
||||
|
||||
This is an [OpenLlama model](https://huggingface.co/openlm-research/open_llama_3b) that has been fine-tuned on 1 epoch of the
|
||||
[AlpacaCode](https://huggingface.co/datasets/mwitiderrick/AlpacaCode) dataset (122K rows).
|
||||
|
||||
## Prompt Template
|
||||
```
|
||||
### Instruction:
|
||||
|
||||
{query}
|
||||
|
||||
### Response:
|
||||
<Leave new line for model to respond>
|
||||
```
|
||||
## Usage
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/open_llama_3b_code_instruct_0.1")
|
||||
model = AutoModelForCausalLM.from_pretrained("mwitiderrick/open_llama_3b_code_instruct_0.1")
|
||||
query = "Write a quick sort algorithm in Python"
|
||||
text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
|
||||
output = text_gen(f"### Instruction:\n{query}\n### Response:\n")
|
||||
print(output[0]['generated_text'])
|
||||
"""
|
||||
### Instruction:
|
||||
write a quick sort algorithm in Python
|
||||
### Response:
|
||||
def quick_sort(arr):
|
||||
if len(arr) <= 1:
|
||||
return arr
|
||||
else:
|
||||
pivot = arr[len(arr) // 2]
|
||||
left = [x for x in arr if x < pivot]
|
||||
middle = [x for x in arr if x == pivot]
|
||||
right = [x for x in arr if x > pivot]
|
||||
return quick_sort(left) + middle + quick_sort(right)
|
||||
|
||||
arr = [5,2,4,3,1]
|
||||
print(quick_sort(arr))
|
||||
"""
|
||||
[1, 2, 3, 4, 5]
|
||||
"""
|
||||
```
|
||||
## Metrics
|
||||
[Detailed metrics](https://huggingface.co/datasets/open-llm-leaderboard/details_mwitiderrick__open_llama_3b_code_instruct_0.1)
|
||||
```
|
||||
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
||||
|----------|-------|------|-----:|------|-----:|---|-----:|
|
||||
|winogrande|Yaml |none | 0|acc |0.6267|± |0.0136|
|
||||
|hellaswag|Yaml |none | 0|acc |0.4962|± |0.0050|
|
||||
| | |none | 0|acc_norm|0.6581|± |0.0047|
|
||||
|arc_challenge|Yaml |none | 0|acc |0.3481|± |0.0139|
|
||||
| | |none | 0|acc_norm|0.3712|± |0.0141|
|
||||
|truthfulqa|N/A |none | 0|bleu_max | 24.2580|± |0.5985|
|
||||
| | |none | 0|bleu_acc | 0.2876|± |0.0003|
|
||||
| | |none | 0|bleu_diff | -8.3685|± |0.6065|
|
||||
| | |none | 0|rouge1_max | 49.3907|± |0.7350|
|
||||
| | |none | 0|rouge1_acc | 0.2558|± |0.0002|
|
||||
| | |none | 0|rouge1_diff|-10.6617|± |0.6450|
|
||||
| | |none | 0|rouge2_max | 32.4189|± |0.9587|
|
||||
| | |none | 0|rouge2_acc | 0.2142|± |0.0002|
|
||||
| | |none | 0|rouge2_diff|-12.9903|± |0.9539|
|
||||
| | |none | 0|rougeL_max | 46.2337|± |0.7493|
|
||||
| | |none | 0|rougeL_acc | 0.2424|± |0.0002|
|
||||
| | |none | 0|rougeL_diff|-11.0285|± |0.6576|
|
||||
| | |none | 0|acc | 0.3072|± |0.0405|
|
||||
```
|
||||
3
open_llama_3b_code_instruct_0.1.fp16.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.fp16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6eceef25bdc21d7e4a50d44d714e3f9767713120a27f056dd3c81c8a4309675f
|
||||
size 6855133024
|
||||
3
open_llama_3b_code_instruct_0.1.q2_k.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.q2_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ed96a2be160ccf77e830a31327c8e7c69c8148983a0830749f355bcbbb2775ba
|
||||
size 2149085088
|
||||
3
open_llama_3b_code_instruct_0.1.q3_k_m.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.q3_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d34bdeb1e47fcfd48095e9cd0eb89c44b002a50ecd2114a075512d274cf350fd
|
||||
size 2271709088
|
||||
3
open_llama_3b_code_instruct_0.1.q4_k_m.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75d2a16810fa0ddb849b6d71d2acd5fd05afd6bfccfad0ec9461ab36785080ea
|
||||
size 2581213088
|
||||
3
open_llama_3b_code_instruct_0.1.q5_k_m.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.q5_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7fa75296fa9146cec320bbdcc7474b302be6ff7108e33ae68881dfb2642d205
|
||||
size 2758173088
|
||||
3
open_llama_3b_code_instruct_0.1.q6_k.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.q6_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f25adb8b24e5a15a52214d35bf8d7787e10d0f4ced135ec6d93648b58817ccfd
|
||||
size 3642973088
|
||||
3
open_llama_3b_code_instruct_0.1.q8_0.gguf
Normal file
3
open_llama_3b_code_instruct_0.1.q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:db03ed426391a12d9344442747b22a4ea89e2fc31ffb1f520161756fe316a21e
|
||||
size 3642973088
|
||||
Reference in New Issue
Block a user