Downloads · 30 days
62
0% of all-time downloads
bhenrym14/airophin-13b-pntk-16k-fp16
airophin-13b-pntk-16k-fp16 is a text generation model from bhenrym14. Use it when you need the model to write or continue text. It is set up for transformers.
GPTQ weights can be found here: https://huggingface.co/bhenrym14/airophin-13b-pntk-16k-GPTQ
Downloads · 30 days
62
0% of all-time downloads
All-time downloads
49.6K
Public
Parameters
13B
26 GB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors26 GB · 100%
How the weights are stored.
F1613B · 100%
From the Hugging Face model README
GPTQ weights can be found here: https://huggingface.co/bhenrym14/airophin-13b-pntk-16k-GPTQ
This is a finetune of Llama-2-13b, intended to extend the useful context window to 16384 tokens. There are two training phases:
This is a QLoRA fine-tune (rank 64).
All training was performed with 1x RTX 6000 Ada.
For the 4096 context length model using airoboros-gpt4-1.4.1 see: Jon Durbin's airoboros-l2-13b-gpt4-1.4.1
This model employs Partial NTK Rope Scaling. This methodology is not yet implemented natively in Transformers or Exllama (as of 7/21). There are three options to run this.
LlamaEmbedding with LlamaPartNTKScaledRotaryEmbedding, with max_position_embeddings=16384 and original_max_position_embeddings=4096. A monkeypatch can be found here.Please comment with any questions. This hasn't been extensively tested.
Methods of extending the useful context window of LLM's have gained significant traction. Several methods requiring little to no finetuning/retraining have emerged. Among these is linear position interpolation kaiokendev and meta AI)) and NTK aware scaling. My prior experiments demonstrate significant performance improvements both from finetuning with these scaling adjustments implemented and with longer sequences.
Unfortunately it has also been shown that LLM's frequently struggle to attend to salient information in the middle of the context window. Attending to nearby tokens is essential to producing syntactically correct and semantically coherent sentences. Essential context is also most commonly found at the beginning of a context window. With this in mind, it is unsurprising LLMs often attend more strongly to these areas. Does this learned model behavior result in an "extrapolated deemphasis" when such embeddings are scaled? This hypothesis may be supported by the material improvements in perplexity achieved by training on long sequences (not just including the RoPE scaling during the fine-tune).
Here I explore whether training on long sequences that have clear conceptual dependencies residing in the middle of the context helps attenuate the difficulties in attending to middle-context tokens. When/if I have time, I hope to perform a more rigorous assessment of the peformance with respect to this specific issue.
| Context (tokens) | bhenrym14/airophin-13b-pntk-16k-fp16 | bhenrym14/airoboros-13b-gpt4-1.4.1-PI-8192-fp16 | bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16 | jondurbin/airoboros-l2-13b-gpt4-1.4.1 |
|---|---|---|---|---|
| 512 | 7.62 | 8.24 | 7.90 | 7.23 |
| 1024 | 6.20 | 6.71 | 6.17 | 5.85 |
| 2048 | 5.38 | 5.87 | 5.23 | 5.07 |
| 4096 | 5.08 | 5.50 | 4.91 | 4.77 |
| 8192 | 4.90 | 5.32 | Not Tested | 57.1 |
| 12000 | 4.82 | 56.1 | Not Tested | Not Tested |
airoboros-like prompting remains. See the following from one of Jon Durbin's airoboros model cards:
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
The only prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
BEGININPUT - denotes a new input blockBEGINCONTEXT - denotes the block of context (metadata key/value pairs) to associate with the current input blockENDCONTEXT - denotes the end of the metadata block for the current inputENDINPUT - denotes the end of the current input blockBEGININSTRUCTION - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.ENDINSTRUCTION - denotes the end of instruction setIt sometimes works without ENDINSTRUCTION, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
And the response:
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
Or:
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
Write a websocket application in node.js. PLAINFORMAT
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
Response:
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
</details>
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
USER: What has a neck but no head?
ASSISTANT: A bottle.
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*