new upload

README.md

@@ -1,199 +1,43 @@
 ---
-library_name: transformers
-tags: []
+license: apache-2.0
+tags:
+- trl
+- ppo
+- transformers
+- reinforcement-learning
 ---
 
-# Model Card for Model ID
+# TRL Model
 
-<!-- Provide a quick summary of what the model is/does. -->
+This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to
+ guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
 
+## Usage
 
+To use this model for inference, first install the TRL library:
 
-## Model Details
+```bash
+python -m pip install trl
+```
 
-### Model Description
+You can then generate text as follows:
 
-<!-- Provide a longer summary of what this model is. -->
+```python
+from transformers import pipeline
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+generator = pipeline("text-generation", model="tzwilliam0/logs_morlhf/maxmin-dpo-init-kl-coef-0.5-fix-lora/batch_16")
+outputs = generator("Hello, my llama is cute")
+```
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
 
-### Model Sources [optional]
+```python
+from transformers import AutoTokenizer
+from trl import AutoModelForCausalLMWithValueHead
 
-<!-- Provide the basic links for the model. -->
+tokenizer = AutoTokenizer.from_pretrained("tzwilliam0/logs_morlhf/maxmin-dpo-init-kl-coef-0.5-fix-lora/batch_16")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("tzwilliam0/logs_morlhf/maxmin-dpo-init-kl-coef-0.5-fix-lora/batch_16")
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
+outputs = model(**inputs, labels=inputs["input_ids"])
+```

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
-    "k_proj",
+    "o_proj",
+    "down_proj",
     "q_proj",
+    "v_proj",
     "up_proj",
-    "o_proj",
-    "v_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
-size 40
+oid sha256:dac7adf35f641a598a1a8cd2e3ae6f1e93b2ed3890c2398a60447d0f11f933bf
+size 2497313944

added_tokens.json

@@ -21,5 +21,6 @@
   "<|video_pad|>": 151656,
   "<|vision_end|>": 151653,
   "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
+  "<|vision_start|>": 151652,
+  "[PAD]": 151666
 }

config.json

@@ -0,0 +1,53 @@
+{
+  "accelerator_kwargs": {},
+  "adap_kl_ctrl": false,
+  "backward_batch_size": 5,
+  "batch_size": 60,
+  "cliprange": 0.2,
+  "cliprange_value": 0.2,
+  "compare_steps": 1,
+  "early_stopping": true,
+  "exp_name": "morlhf",
+  "forward_batch_size": null,
+  "gamma": 1,
+  "global_backward_batch_size": 20,
+  "global_batch_size": 240,
+  "gradient_accumulation_steps": 5,
+  "horizon": 10000,
+  "init_kl_coef": 0.5,
+  "is_encoder_decoder": false,
+  "is_peft_model": true,
+  "kl_penalty": "kl",
+  "lam": 0.95,
+  "learning_rate": 1e-05,
+  "log_with": "wandb",
+  "max_grad_norm": 0.5,
+  "mini_batch_size": 1,
+  "model_name": "unsloth/Qwen2.5-7B",
+  "optimize_cuda_cache": true,
+  "optimize_device_cache": false,
+  "ppo_epochs": 4,
+  "project_kwargs": {},
+  "push_to_hub_if_best_kwargs": {},
+  "query_dataset": "imdb",
+  "ratio_threshold": 10.0,
+  "remove_unused_columns": true,
+  "reward_model": "sentiment-analysis:lvwerra/distilbert-imdb",
+  "score_clip": null,
+  "seed": 0,
+  "steps": 20000,
+  "target": 3,
+  "target_kl": 1,
+  "task_name": null,
+  "tracker_kwargs": {
+    "wandb": {
+      "name": "maxmin-dpo-init-kl-coef-0.5-fix-lora"
+    }
+  },
+  "tracker_project_name": "morlhf",
+  "use_score_norm": false,
+  "use_score_scaling": false,
+  "vf_coef": 0.1,
+  "whiten_rewards": false,
+  "world_size": 4
+}

merges.txt

@@ -308,7 +308,6 @@ tr ing
 o k
 _ _
 c l
-# #
 Ġh e
 ar d
 ) .
@@ -563,7 +562,6 @@ i eld
 Ġp er
 C ont
 ing s
-## ##
 Ġd ata
 Ġs a
 e f
@@ -810,7 +808,6 @@ R es
 is e
 m in
 ĠĠĠĠ Ċ
-# include
 eth od
 . P
 ut e
@@ -1100,7 +1097,6 @@ pr int
 Ex ception
 in put
 Ġtr ans
-#### ####
 ord er
 B y
 Ġa w
@@ -1184,7 +1180,6 @@ if y
 Ġb reak
 Ġ );Ċ
 re n
-# define
 it t
 Ġa p
 ĉ c
@@ -2174,7 +2169,6 @@ s ource
 http s
 Ġd em
 Ġe ar
-######## ########
 Ġm atch
 or ies
 ac es
@@ -2396,7 +2390,6 @@ a ff
 ER R
 Ġ< =
 at ely
-# if
 u ction
 ĠT e
 Ġl ink
@@ -2406,7 +2399,6 @@ u ction
 m e
 Ġg iven
 O ut
-# endif
 Ġbet ter
 P age
 Ġfe el
@@ -4699,7 +4691,6 @@ c ard
 o ch
 _ image
 \ t
-# Ċ
 ( L
 Ġindu stry
 com ing
@@ -4769,7 +4760,6 @@ SS ION
 Ġcurrent ly
 se c
 Ġrelations hip
-################ ################
 ĠM ap
 as et
 Ġparam eters
@@ -5271,7 +5261,6 @@ l at
 ast e
 Ġpro file
 Ġread y
-#if ndef
 ro te
 Ġs ense
 G ener
@@ -5496,7 +5485,6 @@ ag ram
 Ġp en
 .b tn
 ĠA S
-#if def
 Ġcho ice
 ĠP age
 _P RO
@@ -5656,7 +5644,6 @@ b uf
 S cript
 d at
 Ġr ule
-# import
 =" /
 S erial
 Ġstart ing
@@ -6233,7 +6220,6 @@ C D
 ib ly
 .e quals
 Ġintern ational
-# pragma
 oo th
 W riter
 i ate
@@ -7753,7 +7739,6 @@ D on
 ĠH ot
 ĠInd ex
 ; &
-# !
 ĠN or
 ĠC ap
 - (
@@ -7908,7 +7893,6 @@ ant ic
 ĠApp le
 g in
 Re quired
-# +
 land s
 Ġs qu
 Ġfact or
@@ -8444,7 +8428,6 @@ C OM
 i ro
 Ġrem ote
 ĠI T
-#! /
 Ġred istrib
 ra z
 ĠS ince
@@ -9682,7 +9665,6 @@ ont o
 ĠJ ournal
 r outer
 Ġmys qli
-# else
 ) "
 -x s
 let s
@@ -11771,7 +11753,6 @@ R et
 -d anger
 Ġroom s
 con v
-# {
 . op
 ĠA rea
 _S C
@@ -12810,7 +12791,6 @@ Th ank
 Ġfact s
 Ġun t
 .in stance
-################################ ################################
 - end
 ĠJO IN
 ĠH en
@@ -13096,7 +13076,6 @@ id os
 ĠJew ish
 Ġre covery
 Ġstand s
-# [
 Ġafter noon
 ĠArt icle
 _ att
@@ -13632,7 +13611,6 @@ un ge
 err a
 Ċ ĠĠĊ
 utor ial
-# a
 p ay
 char ge
 ĠI re
@@ -14117,7 +14095,6 @@ im plementation
 Ġstre ets
 _M SG
 New s
-## #
 : /
 Ġcut ting
 x B
@@ -15933,7 +15910,6 @@ param eter
 gener ated
 Ġad mitted
 Ġp ussy
-# w
 Ġsw im
 un ion
 N a
@@ -15985,7 +15961,6 @@ _ div
 vel y
 } );čĊ
 _ ENT
-#+ #+
 art icles
 ĠSou thern
 Ġstrong er
@@ -17198,7 +17173,6 @@ _f ont
 Ġcharacter istics
 D one
 el n
-######## ####
 PO S
 Ġd ensity
 ĠPl atform
@@ -18203,7 +18177,6 @@ W T
 d og
 Ġclick ing
 ), ĊĊ
-# line
 Oper ator
 Ġc iv
 Ġm erg
@@ -19615,7 +19588,6 @@ _th eme
 Ġdemonstr ate
 ĠHow ard
 D rop
-# undef
 Ġinv oke
 ĠB ridge
 end en
@@ -22357,7 +22329,6 @@ L F
 ĠP ub
 Ġâ Ķ
 c ion
-## Ċ
 II I
 Tag Name
 Ġam id
@@ -23407,7 +23378,6 @@ w ers
 .m aterial
 ĠD ue
 ĠP el
-# print
 Ġindepend ence
 ex us
 Sh adow
@@ -26230,7 +26200,6 @@ p icture
 ĠFant asy
 st ory
 Ġm ême
-# ĊĊ
 _s lice
 olt age
 H ar
@@ -26583,7 +26552,6 @@ j query
 am ination
 [ @"
 Ġm uj
-## #Ċ
 First OrDefault
 then Return
 C he
@@ -26755,7 +26723,6 @@ enc oder
 ather ine
 ( dest
 az ed
-# endregion
 sem bl
 , M
 ob y
@@ -28592,7 +28559,6 @@ _S M
 ib o
 Ġlo yal
 Ġuse less
-# elif
 ĠUlt imate
 C ome
 g el
@@ -28800,7 +28766,6 @@ as il
 ation ally
 ĠMe eting
 è¯ ¯
-# region
 Ġrout ing
 .f ocus
 ĠYou th
@@ -29597,7 +29562,6 @@ index Of
 .prot ocol
 AF E
 Ġtext ures
-################################ ################
 umb ai
 .st ats
 ĠG E
@@ -31784,7 +31748,6 @@ k now
 .F ull
 . undefined
 ĠSequ elize
-################################################################ ############
 Ġeduc ated
 _O VER
 åº ı
@@ -33396,7 +33359,6 @@ M id
 dd s
 Ġdepos its
 ĉd river
-# ga
 pr ising
 print ln
 Ġpres enter
@@ -40229,7 +40191,6 @@ M ade
 ac ific
 .v olume
 Ġmir rors
-################################################################ ################
 Ġviol ate
 ars ers
 Ġsoc io
@@ -41087,7 +41048,6 @@ _N ode
 ar de
 Ġfier ce
 lic ted
-# čĊ
 Ġbreak through
 ĠE rik
 Ġb ride
@@ -43830,7 +43790,6 @@ _ Log
 rown ed
 _m ed
 ĉ date
-# __
 Ġcost umes
 ĠRe quires
 aff le
@@ -45895,7 +45854,6 @@ Progress HUD
 Ġmock ed
 ĠT ory
 Ġ") ";Ċ
-# g
 Ġli ed
 Ġs vc
 _g ui
@@ -47820,12 +47778,10 @@ Num ero
 d aily
 ĠC oding
 ( destination
-# $
 uj Äħ
 Ġemerg ence
 _p ara
 _IN CLUDE
-# :
 Ġrecogn izing
 Ġf ug
 "} },Ċ
@@ -48241,7 +48197,6 @@ b stract
 k p
 IT ES
 Ġ ################################################################
-# get
 / Desktop
 ĉgl m
 Ġz inc
@@ -50267,7 +50222,6 @@ _L AYER
 Ġdee pest
 w k
 ĠNo ise
-### ĊĊ
 Ġpr éc
 ot le
 ÑĤ е
@@ -52067,7 +52021,6 @@ C OR
 -effect ive
 Ġsk u
 ed ly
-## ĊĊ
 ĠH olly
 ĠFL ASH
 / TR
@@ -55286,7 +55239,6 @@ keep ers
 _s b
 om ens
 ĠExec utes
-# "
 TT Y
 ĠValue Type
 ); */Ċ
@@ -55686,7 +55638,6 @@ S cores
 E OS
 H al
 Ġtrust worthy
-# =
 .EX TRA
 Ġman o
 is icing
@@ -60521,7 +60472,6 @@ m om
 / place
 Ġhol istic
 : t
-# ,
 Ġb oto
 Ġnause a
 ĠSh ooting
@@ -60658,7 +60608,6 @@ IM ATION
 C ause
 at ypes
 man ufacturer
-# ----------------------------------------------------------------------------
 Ġsp or
 es on
 Ġpun ched
@@ -62268,7 +62217,6 @@ Set Branch
 S creenshot
 esthes ia
 Ġwalk er
-# from
 co ordinate
 _ interest
 Ġhelp less
@@ -63479,7 +63427,6 @@ Count s
 Field Type
 ok able
 ĠRT L
-# index
 Ġ% {
 Ġar ist
 .Get Mapping
@@ -65802,7 +65749,6 @@ tr uncate
 so on
 Ġdis fr
 ĉ Vec
-## _
 .s chool
 Ġbl inds
 Ġac ab
@@ -67074,7 +67020,6 @@ _IO CTL
 ĉex ec
 EN AME
 _ letters
-#### #
 ĠC s
 '] =="
 Ġ" ')
@@ -67276,7 +67221,6 @@ _ asm
 Ġtem pl
 ĠExp ense
 e ight
-# SBATCH
 z ones
 .p arts
 at rice
@@ -67611,7 +67555,6 @@ ra i
 i ard
 Theme Provider
 Ġevent Data
-# ad
 .get Url
 Ġtool box
 Ġover riding
@@ -68456,7 +68399,6 @@ _PRE SENT
 ĠTh eta
 _inter p
 R aster
-# error
 , obj
 Ġtweet ing
 _G PU
@@ -68804,7 +68746,6 @@ imm une
 Ġè¾ĵ åħ¥
 Ġintimid ation
 end ale
-################################################################ ########
 Ġinsight ful
 Ġs ands
 Ġphotograph ic
@@ -69210,7 +69151,6 @@ sh ed
 Dep loy
 .Con tract
 - bo
-# /
 Ġinter ception
 Ġis bn
 Ġman ners
@@ -69693,7 +69633,6 @@ PO CH
 \ \"
 - job
 Ġsevent y
-#### Ċ
 ĠMan or
 Ġdown right
 Ġtime frame
@@ -71499,7 +71438,6 @@ _BR ANCH
 /m essages
 Ġof Type
 ĉs wap
-# plt
 ĠTur ks
 N ES
 Ġprogress ively
@@ -71747,7 +71685,6 @@ L ik
 _T itle
 (G tk
 Ġc elle
-# ================================================================
 ĠJ oomla
 "> //
 Month ly
@@ -75253,7 +75190,6 @@ s olver
 ĠRevel ation
 Ġrap ide
 p unk
-# ----------------------------------------------------------------
 Object Id
 abin et
 extr acomment
@@ -75658,7 +75594,6 @@ h ari
 (c d
 Ġun zip
 Ġglam orous
-# ",
 Ġn aw
 Ġmin ib
 ĠBr an
@@ -75941,7 +75876,6 @@ Button Type
 Ġragaz za
 / tag
 Ġirres ist
-# End
 ****** *čĊ
 Ġrestr ained
 Ġch iropr
@@ -76079,7 +76013,6 @@ cast ing
 Ġgr âce
 ĠH elsinki
 G ro
-# af
 ìĭ Ŀ
 Ġsou ha
 ĠInd ie
@@ -76872,7 +76805,6 @@ x EE
 .M ESSAGE
 (de g
 å¿ Ĺ
-#### ##
 Ġ"" ),
 kl är
 \M ail
@@ -77087,7 +77019,6 @@ ren s
 / grid
 Ġfil thy
 .e v
-#### #Ċ
 Ġs are
 Ġso aking
 ĠReg ions
@@ -77328,7 +77259,6 @@ IFICATION S
 ` ;
 ãĥ ĭ
 cent e
-# ab
 Ġlex ical
 ĠB RO
 Ġr ulings
@@ -77437,7 +77367,6 @@ U PI
 ĉ props
 Ġrot ten
 Re jected
-# ac
 . ua
 ĠAm nesty
 Ġpenn ed
@@ -77780,7 +77709,6 @@ d pi
 cul os
 _person al
 Ġanaly tic
-# create
 _mem cpy
 (List Node
 _T ag
@@ -78698,7 +78626,6 @@ b anks
 ìŀħ ëĭĪëĭ¤
 Ġsid eline
 .Array Adapter
-#### ##Ċ
 ĠSy rians
 ĠAtt endance
 -es que
@@ -79191,7 +79118,6 @@ Image Url
 ALL ERY
 c j
 x AD
-############################################################################ ###Ċ
 Ġitalian i
 | #
 Ġreg enerate
@@ -80160,7 +80086,6 @@ op he
 _C ategory
 ĠBT N
 ĠDar th
-# for
 eth nic
 arch itecture
 ĠCou pe
@@ -81235,7 +81160,6 @@ _TRA IN
 Ġcooper ating
 ung i
 Ar izona
-# echo
 -ex pression
 .min utes
 Ġpref ixed
@@ -81767,7 +81691,6 @@ customer Id
 ĠMom ents
 enu ous
 IFIC ATE
-#### ###Ċ
 æĸĩ ç«ł
 á»į c
 orm sg
@@ -81815,7 +81738,6 @@ Environment al
 ĠIS IL
 Ġco op
 h ores
-# @
 Ġcomp el
 (s kip
 éĺ ³
@@ -82040,7 +81962,6 @@ ia ux
 Ġ-*- čĊ
 if es
 ĠM ansion
-# Region
 C ancellation
 Ġnear ing
 Ġl angu
@@ -82321,7 +82242,6 @@ M ismatch
 Ġw reak
 Mar vel
 /s l
-################################ ########
 Ġmov able
 Ñĥ й
 ĠDr inking
@@ -83897,7 +83817,6 @@ M iami
 ĠPal o
 ĠSuz anne
 _m appings
-#{ @
 ĠOccup ational
 _b uckets
 go als
@@ -84042,7 +83961,6 @@ so v
 -w atch
 ĠHosp itals
 } while
-################ ########
 á» £
 Ġakt ual
 Ġkil ograms
@@ -84164,7 +84082,6 @@ CH AN
 Ġcurrent Position
 ĠCaucas ian
 $ img
-# aa
 Ġse an
 M ess
 *= *=
@@ -85109,7 +85026,6 @@ py x
 ĠR udd
 ĠPres byterian
 und ler
-#! [
 _l ahir
 () =="
 Access ibility
@@ -87589,7 +87505,6 @@ C ouncil
 _AT OMIC
 Sub Menu
 _com press
-# .
 Dr v
 .push Button
 Ġsuit case
@@ -87648,7 +87563,6 @@ ch ine
 Ġe books
 ) size
 Ġspecial ised
-# ae
 Ġmich ael
 ĠSTD OUT
 ĠP ell
@@ -87827,7 +87741,6 @@ t ournament
 ĠEisen hower
 File d
 Ġhe bt
-# \
 create QueryBuilder
 æľī æķĪ
 v anced
@@ -87843,7 +87756,6 @@ Inst aller
 ol vable
 Ġal as
 (sp ell
-################ ############
 Ġdef amation
 ( Arg
 Ġuser Details
@@ -89781,7 +89693,6 @@ ict ory
 Ġsup p
 pe on
 v rier
-################################################ ########
 Ġtrot z
 Ġmel tdown
 ark ers
@@ -90473,7 +90384,6 @@ Gr an
 ser ter
 Ġstore front
 _ ends
-################################################################################ Ċ
 ĉg it
 D SP
 CH AIN
@@ -91996,7 +91906,6 @@ arg ed
 ĠST ILL
 Qualified Name
 . RES
-# c
 .w riteln
 ĠImmutable List
 ĠTh umb
@@ -92978,7 +92887,6 @@ Sc ala
 in ne
 ĠCONST ANTS
 _P rice
-# %%
 Ġar sch
 ĠNS AttributedString
 ĠFile Type
@@ -93925,7 +93833,6 @@ _TRI ANGLE
 _P ICTURE
 _OR IENTATION
 ĠO PP
-# '
 áf ico
 .h istogram
 ĠB enny
@@ -94196,7 +94103,6 @@ Owner Id
 ew n
 Ġpop ulous
 ĠSh ed
-# ${
 ĠA lo
 Device Info
 (IN VOKE
@@ -97587,7 +97493,6 @@ F el
 ĠD ISTRIBUT
 é ments
 ĠValid ates
-################################################ ############
 Ġ| /
 Ġes l
 Ġré seau
@@ -97607,7 +97512,6 @@ Ne o
 ime i
 .get Bounds
 .Mouse EventHandler
-#### ###
 Generic Type
 /c ms
 Ġturn o

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd15b2ea09dab8410e9d4ad0456b17d39d44c3e8659d7f2da832d53ed36f2711
+size 15868

special_tokens_map.json

@@ -14,15 +14,29 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|PAD_TOKEN|>",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2,6 +2,30 @@
   "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
+    "128244": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "151643": {
       "content": "<|endoftext|>",
       "lstrip": false,
@@ -185,6 +209,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151666": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -202,14 +234,14 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "bos_token": null,
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "</s>",
   "errors": "replace",
   "model_max_length": 131072,
-  "pad_token": "<|PAD_TOKEN|>",
+  "pad_token": "[PAD]",
   "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "unk_token": "<unk>"
 }