初始化项目，由ModelHub XC社区提供模型
Model: RichardErkhov/tartuNLP_-_Llammas-gguf Source: Original Platform
This commit is contained in:
ModelHub XC
57
.gitattributes
vendored
Normal file
57
.gitattributes
vendored
Normal file
@@ -0,0 +1,57 @@
|
||||
*.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
|
||||
Llammas.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llammas.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Llammas.IQ3_M.gguf
Normal file
3
Llammas.IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd210651efd7b260a23fa62ea0f8900c60087636a3582396e82fd0be9283a8fa
|
||||
size 3114865184
|
||||
3
Llammas.IQ3_S.gguf
Normal file
3
Llammas.IQ3_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29cfe0561b66998a37e577db7a158395dbde303dd3c77b4824a3eae70e19e076
|
||||
size 2948305440
|
||||
3
Llammas.IQ3_XS.gguf
Normal file
3
Llammas.IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b85df8186cfcb43a9798760a90437b94cc765fad3acea0be76cb5749244211a6
|
||||
size 2796524064
|
||||
3
Llammas.IQ4_NL.gguf
Normal file
3
Llammas.IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:504693ab66ae4354da0e8f7b216823c1e4eda44137751bb4f5560078a62b5d30
|
||||
size 3848352288
|
||||
3
Llammas.IQ4_XS.gguf
Normal file
3
Llammas.IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6e89e2ea17a66347f96319ea9f6e8ca3c70546f372c911339e889a3c4658bd16
|
||||
size 3647517216
|
||||
3
Llammas.Q2_K.gguf
Normal file
3
Llammas.Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e1726d9fd1d7f79361c91ed5df06aa420dd2cf556692878783456eea9eae70b2
|
||||
size 2532864544
|
||||
3
Llammas.Q3_K.gguf
Normal file
3
Llammas.Q3_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7ef90295ea140a9fd35f6d689eb310155bb904b0b80bece0f77e4525416ad288
|
||||
size 3298005536
|
||||
3
Llammas.Q3_K_L.gguf
Normal file
3
Llammas.Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:63e4007847ea0064587dc82e7cbd3d72b02f691f6974decfc1a10c91ce613074
|
||||
size 3597111840
|
||||
3
Llammas.Q3_K_M.gguf
Normal file
3
Llammas.Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7ef90295ea140a9fd35f6d689eb310155bb904b0b80bece0f77e4525416ad288
|
||||
size 3298005536
|
||||
3
Llammas.Q3_K_S.gguf
Normal file
3
Llammas.Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e67ff988f772f6823329f6063cae96d41699850f52882fd864eb8a726f844a49
|
||||
size 2948305440
|
||||
3
Llammas.Q4_0.gguf
Normal file
3
Llammas.Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3531184bdae2a35fad15d6ac5bb7bcb6e30ace6295610de312938e9737ba4347
|
||||
size 3825807904
|
||||
3
Llammas.Q4_1.gguf
Normal file
3
Llammas.Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71498ca614ccee82e0819e9b54377b766773ce597d2a79fd80f33d2b2141b883
|
||||
size 4238750240
|
||||
3
Llammas.Q4_K.gguf
Normal file
3
Llammas.Q4_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e31e7feb93c8e83c745ab4d8820a461365b040a2743395b837c864ae670be769
|
||||
size 4081005088
|
||||
3
Llammas.Q4_K_M.gguf
Normal file
3
Llammas.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e31e7feb93c8e83c745ab4d8820a461365b040a2743395b837c864ae670be769
|
||||
size 4081005088
|
||||
3
Llammas.Q4_K_S.gguf
Normal file
3
Llammas.Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f627454a4049553c11a2a0444b3c6dd9b94380c57dfb9d85a0928eb145b15737
|
||||
size 3856740896
|
||||
3
Llammas.Q5_0.gguf
Normal file
3
Llammas.Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:60137955ccfd1e8053bd3fe36b423e7501217e9444a5624a6b6369860b3abcde
|
||||
size 4651692576
|
||||
3
Llammas.Q5_1.gguf
Normal file
3
Llammas.Q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0f97ca7663ef9c9968931a275c409f90413a44958ec3d09c7ffd29d3a190e163
|
||||
size 5064634912
|
||||
3
Llammas.Q5_K.gguf
Normal file
3
Llammas.Q5_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:30067f342f2339ea16598df2f70a74d4f3afbe92953b9d37177c947a95baf2d0
|
||||
size 4783157792
|
||||
3
Llammas.Q5_K_M.gguf
Normal file
3
Llammas.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:30067f342f2339ea16598df2f70a74d4f3afbe92953b9d37177c947a95baf2d0
|
||||
size 4783157792
|
||||
3
Llammas.Q5_K_S.gguf
Normal file
3
Llammas.Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b7edd7c281275e9229d44b259413c7b989bfbfddb22e867b1121b399383162c
|
||||
size 4651692576
|
||||
3
Llammas.Q6_K.gguf
Normal file
3
Llammas.Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:506e1d41a24d87671df5c56bc07893ca2acfc93b726d0a84f84dab6fbc7db9ee
|
||||
size 5529195040
|
||||
3
Llammas.Q8_0.gguf
Normal file
3
Llammas.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8184395b9f1952b5326409aaa4544c0ec538fb283c04e7bc4d21e4d0f3ee6fd4
|
||||
size 7161090592
|
||||
133
README.md
Normal file
133
README.md
Normal file
@@ -0,0 +1,133 @@
|
||||
Quantization made by Richard Erkhov.
|
||||
|
||||
[Github](https://github.com/RichardErkhov)
|
||||
|
||||
[Discord](https://discord.gg/pvy7H8DZMG)
|
||||
|
||||
[Request more models](https://github.com/RichardErkhov/quant_request)
|
||||
|
||||
|
||||
Llammas - GGUF
|
||||
- Model creator: https://huggingface.co/tartuNLP/
|
||||
- Original model: https://huggingface.co/tartuNLP/Llammas/
|
||||
|
||||
|
||||
| Name | Quant method | Size |
|
||||
| ---- | ---- | ---- |
|
||||
| [Llammas.Q2_K.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q2_K.gguf) | Q2_K | 2.36GB |
|
||||
| [Llammas.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
|
||||
| [Llammas.IQ3_S.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.IQ3_S.gguf) | IQ3_S | 2.75GB |
|
||||
| [Llammas.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
|
||||
| [Llammas.IQ3_M.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.IQ3_M.gguf) | IQ3_M | 2.9GB |
|
||||
| [Llammas.Q3_K.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q3_K.gguf) | Q3_K | 3.07GB |
|
||||
| [Llammas.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
|
||||
| [Llammas.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
|
||||
| [Llammas.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
|
||||
| [Llammas.Q4_0.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q4_0.gguf) | Q4_0 | 3.56GB |
|
||||
| [Llammas.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
|
||||
| [Llammas.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
|
||||
| [Llammas.Q4_K.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q4_K.gguf) | Q4_K | 3.8GB |
|
||||
| [Llammas.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
|
||||
| [Llammas.Q4_1.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q4_1.gguf) | Q4_1 | 3.95GB |
|
||||
| [Llammas.Q5_0.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q5_0.gguf) | Q5_0 | 4.33GB |
|
||||
| [Llammas.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
|
||||
| [Llammas.Q5_K.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q5_K.gguf) | Q5_K | 4.45GB |
|
||||
| [Llammas.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
|
||||
| [Llammas.Q5_1.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q5_1.gguf) | Q5_1 | 4.72GB |
|
||||
| [Llammas.Q6_K.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q6_K.gguf) | Q6_K | 5.15GB |
|
||||
| [Llammas.Q8_0.gguf](https://huggingface.co/RichardErkhov/tartuNLP_-_Llammas-gguf/blob/main/Llammas.Q8_0.gguf) | Q8_0 | 6.67GB |
|
||||
|
||||
|
||||
|
||||
|
||||
Original model description:
|
||||
---
|
||||
language:
|
||||
- et
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- conversational
|
||||
---
|
||||
|
||||
# LLammas 🐑
|
||||
|
||||
Llama-2-7B finetuned in two stages:
|
||||
1. 5B tokens of CulturaX with 75% of documents in Estonain and 25% in English (see [Llammas-base](https://huggingface.co/tartuNLP/Llammas-base)),
|
||||
2. Alpaca-cleaned, Alpaca-est, OASST1 top-1 English conversations, CoT and FLAN-V2 following open-instruct (both 10,000), WMT18 English-Estonian translation development data (as documents), general MTee validation English-Estonian held-out data.
|
||||
|
||||
[Alpaca-est](https://github.com/TartuNLP/alpaca-est) is an instruction dataset generated for Estonian with *gpt-3.5-turbo-0613*, following Alpaca. More details in our [paper](https://arxiv.org/abs/2404.04042).
|
||||
|
||||
Additional resources:
|
||||
* Paper: [arxiv.org/abs/2404.04042](https://arxiv.org/abs/2404.04042)
|
||||
* Code: [github.com/TartuNLP/llammas](https://github.com/TartuNLP/llammas)
|
||||
* Base model: [tartuNLP/Llammas-base](https://huggingface.co/tartuNLP/Llammas-base)
|
||||
* 4-bit quantized model in GGUF: [AlbertUnn/LlammasGGUF](https://huggingface.co/AlbertUnn/LlammasGGUF)
|
||||
* Alpaca-est dataset: [github.com/TartuNLP/alpaca-est](https://github.com/TartuNLP/alpaca-est)
|
||||
|
||||
### Using the model
|
||||
|
||||
|
||||
|
||||
Using the model in a text-generation pipeline:
|
||||
```
|
||||
from transformers import pipeline
|
||||
import torch
|
||||
|
||||
pipe = pipeline("text-generation", model="tartuNLP/Llammas", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Tere!"},
|
||||
{"role": "assistant", "content": "Tere! Kas saaksin teid kuidagi aidata?"},
|
||||
{"role": "user", "content": "Kuidas alustada kirja kirjutamist?"}
|
||||
]
|
||||
|
||||
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.6, top_k=50, top_p=0.9)
|
||||
print(outputs[0]["generated_text"][len(prompt):])
|
||||
```
|
||||
|
||||
|
||||
Using the model in a conversational pipeline (works with transformers==4.36.2, issues with output in newer versions):
|
||||
```
|
||||
from transformers import pipeline, Conversation
|
||||
import torch
|
||||
|
||||
pipe = pipeline("conversational", model="tartuNLP/Llammas", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Tere!"},
|
||||
{"role": "assistant", "content": "Tere! Kas saaksin teid kuidagi aidata?"},
|
||||
{"role": "user", "content": "Kuidas alustada kirja kirjutamist?"}
|
||||
]
|
||||
|
||||
conversation = Conversation(messages)
|
||||
conversation = pipe(conversation)
|
||||
```
|
||||
|
||||
Conversational format:
|
||||
```
|
||||
<|user|>
|
||||
Tere!
|
||||
<|assistant|>
|
||||
Tere! Kas saaksin teid kuidagi aidata?</s>
|
||||
<|user|>
|
||||
Kuidas alustada kirja kirjutamist?
|
||||
<|assistant|>
|
||||
Kirja kirjutamiseks alustage tervitusega, näiteks "Tere!" või "Tere hommikust!". Seejärel tutvustage ennast ja mainige, kellega kirjutate. Kirjeldage oma mõtteid või küsimusi, mida soovite arutada. Lõpetage kiri viisakalt, näiteks "Tänan teid tähelepanu eest!" või "Parimate soovidega!"</s>
|
||||
```
|
||||
|
||||
### Citation
|
||||
```
|
||||
@misc{kuulmets2024teaching,
|
||||
title={Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer},
|
||||
author={Hele-Andra Kuulmets and Taido Purason and Agnes Luhtaru and Mark Fishel},
|
||||
year={2024},
|
||||
eprint={2404.04042},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL}
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user